© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169924
    Prev
    Next
    INDEX
    Explanations

    today, nowadays

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

    sexually explicit or illegal content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    "_
    0.45
     čega
    0.44
    down
    0.42
    掉了
    0.42
    édé
    0.42
    PIL
    0.41
    启用
    0.41
     PIL
    0.40
    ada
    0.40
    ava
    0.40
    POSITIVE LOGITS
     norte
    0.52
     blunder
    0.48
    佞
    0.46
     passeio
    0.46
     diaz
    0.46
     grop
    0.45
     seien
    0.45
    Saludos
    0.45
     solen
    0.45
     pundits
    0.45
    Activations Density 0.004%

    No Known Activations