© 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. 9239
    Prev
    Next
    INDEX
    Explanations

    Spanish phrases and closing punctuation

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

    The neuron fires strongly on low‐frequency “content” tokens—e.g. numbers, decimal measurements, proper names, and other rare or technical words.

    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
    捃
    1.03
    بیداری
    0.91
    ᱯ
    0.91
    eserc
    0.88
    ɖ
    0.88
    ƅ
    0.88
    krieg
    0.88
    粓
    0.86
    որ
    0.86
    뛴
    0.86
    POSITIVE LOGITS
    ,
    0.83
     (
    0.73
     Gare
    0.70
     gloves
    0.68
     sparking
    0.68
     vehicles
    0.66
     scratching
    0.66
    ાય
    0.65
     strands
    0.65
     GAR
    0.65
    Activations Density 0.000%

    No Known Activations