© 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. 258977
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    મેન્ટ
    0.54
     допъл
    0.54
    Კ
    0.54
    崱
    0.53
    <unused92>
    0.53
    <unused20>
    0.52
    <unused35>
    0.52
    мено
    0.52
    蠵
    0.52
    刓
    0.52
    POSITIVE LOGITS
    ,
    0.60
     a
    0.59
     –
    0.57
     to
    0.57
     what
    0.54
    ↵
    0.54
     M
    0.52
     of
    0.51
     P
    0.51
     experimentally
    0.51
    Activations Density 0.000%

    No Known Activations