© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4289
    Prev
    Next
    INDEX
    Explanations

    bash commands and scripts

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

    This neuron responds to uncommon, content-heavy tokens (i.e. infrequent or technical words) in the text.

    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
    Paint
    0.76
    Ï
    0.76
    Ε
    0.75
    C
    0.74
    P
    0.74
    Cu
    0.73
    Pipe
    0.73
    E
    0.71
    Limited
    0.70
    Current
    0.70
    POSITIVE LOGITS
    をはじめ
    1.00
     Nome
    1.00
     Recordemos
    0.99
     Inglaterra
    0.96
     Lleg
    0.94
     aconsel
    0.94
     Mesmo
    0.92
     Donnerstag
    0.89
     roupa
    0.89
     Cependant
    0.89
    Activations Density 0.000%

    No Known Activations