© 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. 134975
    Prev
    Next
    INDEX
    Explanations

    website 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
    can
    0.45
    amiliar
    0.43
    letown
    0.43
    In
    0.42
    .
    0.41
    enciales
    0.40
    aren
    0.40
    ailing
    0.40
    beck
    0.40
    ./
    0.39
    POSITIVE LOGITS
     เอา
    0.43
     साइज
    0.42
     pétales
    0.42
     logarithms
    0.42
     pièce
    0.41
     строение
    0.41
     waistcoat
    0.40
    フォル
    0.40
     размеры
    0.40
    去掉
    0.40
    Activations Density 0.002%

    No Known Activations