© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    handling API, analyze data

    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
     avut
    0.33
     Instit
    0.32
     attuale
    0.32
    茉
    0.32
    骡
    0.31
     amministrat
    0.31
     mnoh
    0.31
     Jad
    0.30
     Jasmine
    0.30
     клуба
    0.30
    POSITIVE LOGITS
    piece
    0.34
    Piece
    0.32
    OCCO
    0.31
    ight
    0.30
    izr
    0.29
    ap
    0.29
    prec
    0.28
    Rs
    0.28
    f
    0.28
    radius
    0.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.