© 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. 195308
    Prev
    Next
    INDEX
    Explanations

    EVA construction, rubber handle, stated above

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

    virtual console or LP base

    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
    or
    0.52
     रखते
    0.48
    >
    0.47
     भरी
    0.46
     veya
    0.45
     動
    0.45
    或
    0.43
     మంది
    0.43
     आधी
    0.42
    response
    0.42
    POSITIVE LOGITS
     vultures
    0.49
     intang
    0.48
     F
    0.48
     begin
    0.46
    बन
    0.46
     camels
    0.46
     walls
    0.46
     résumé
    0.45
     ét
    0.44
     válv
    0.44
    Activations Density 0.001%

    No Known Activations