© 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. 133341
    Prev
    Next
    INDEX
    Explanations

    himwith

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

    originally eaten

    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
     revisit
    0.46
     expedite
    0.46
     airborne
    0.45
    ,
    0.45
     sze
    0.44
     expedited
    0.43
     bogged
    0.43
     identically
    0.43
    ör
    0.42
     discuss
    0.42
    POSITIVE LOGITS
     Seat
    0.53
    Seat
    0.50
    ｲ
    0.48
     Laugh
    0.47
    侶
    0.47
    હાસ
    0.46
    狎
    0.46
    Behaviours
    0.45
    دیای
    0.43
    โพ
    0.43
    Activations Density 0.000%

    No Known Activations