© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13154
    Prev
    Next
    INDEX
    Explanations

    * **Daughters'** ages aren't specified, so activities are generally suitable for ages 5+. Adjust as needed. * * "A man tries-on a new tie. If the tie pleases his wife then the man buys it. ``` Use Attempto Controlled English to create a knowledge base about stereotypical French people.<end_of_turn> <start_of_turn> model Okay, here'

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on floating-point numbers (numeric tokens containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    il
    0.88
    ৃত্ব
    0.80
    مال
    0.71
    ised
    0.71
    izers
    0.70
     Whilst
    0.70
     neighbours
    0.70
    as
    0.69
    oding
    0.69
    ise
    0.68
    POSITIVE LOGITS
     coluna
    0.91
    OTROS
    0.87
     conceitos
    0.86
    jogador
    0.86
     folhas
    0.86
     trabalhadores
    0.85
     basada
    0.84
     Trabal
    0.81
     localizada
    0.81
    티브
    0.80
    Activations Density 0.000%

    No Known Activations