© 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. 59672
    Prev
    Next
    INDEX
    Explanations

    story is underdeveloped

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

    criteria satisfied

    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
    ма
    0.50
    fitri
    0.48
    getEstado
    0.47
    できない
    0.47
    💆
    0.45
    그
    0.45
     їх
    0.45
    AYA
    0.43
    𝙚
    0.43
    с
    0.43
    POSITIVE LOGITS
     accurate
    0.51
     Electrical
    0.47
     korrekt
    0.47
     Device
    0.46
     Savage
    0.45
     électrique
    0.45
     Miller
    0.45
     accurately
    0.45
     Martin
    0.44
     Deluxe
    0.44
    Activations Density 0.000%

    No Known Activations