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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11701
    Prev
    Next
    INDEX
    Explanations

    is

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Hệ
    0.85
     familiarize
    0.84
     território
    0.80
     hệ
    0.79
     Clas
    0.79
    alámb
    0.78
     territor
    0.77
     بِ
    0.77
    t
    0.76
     finalizing
    0.75
    POSITIVE LOGITS
    PT
    0.80
    OA
    0.80
    .
    0.80
    $('.
    0.79
    IG
    0.79
    OP
    0.76
    AV
    0.75
    wh
    0.75
    TT
    0.74
    WH
    0.71
    Activations Density 0.000%

    No Known Activations