© 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. 240395
    Prev
    Next
    INDEX
    Explanations

    colors reflect

    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
     લા
    0.53
     actuel
    0.53
    èvement
    0.52
    atisme
    0.52
    <unused64>
    0.51
     installé
    0.51
     japonais
    0.51
    antik
    0.51
    ujourd
    0.50
    kách
    0.49
    POSITIVE LOGITS
    \
    0.54
    ,
    0.46
     Trou
    0.45
    Whether
    0.45
    Its
    0.43
    тном
    0.43
    用
    0.42
    、
    0.42
    if
    0.41
    $-$
    0.41
    Activations Density 0.000%

    No Known Activations