© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64624
    Prev
    Next
    INDEX
    Explanations

    instagram, favourite, leaves

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

    AI, tech, calculated

    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
     $
    0.56
    <0x0D>
    0.53
     $+
    0.49
     vanished
    0.48
    なども
    0.44
    $
    0.44
     $=
    0.44
    バイ
    0.43
     ৬৬
    0.43
    する
    0.42
    POSITIVE LOGITS
     Làm
    0.46
     Shipbuilding
    0.45
    ρούν
    0.45
    芜
    0.45
     vườn
    0.43
     لمح
    0.43
     كافة
    0.43
     selv
    0.43
     Trains
    0.43
    罾
    0.42
    Activations Density 0.000%

    No Known Activations