© 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. 192008
    Prev
    Next
    INDEX
    Explanations

    way to expand

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

    Sundry, fancy, climb, convert

    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
     consistente
    0.52
    ח
    0.52
    哥哥
    0.50
     ಕೆಲವು
    0.49
     Bruder
    0.49
    cookies
    0.47
    timestamps
    0.47
    ccccn
    0.47
    ଲ
    0.46
    כ
    0.46
    POSITIVE LOGITS
     empath
    0.48
     empathetic
    0.47
     intellect
    0.45
    vić
    0.43
     fantastical
    0.42
     chairman
    0.42
     фанта
    0.42
     canals
    0.42
     tonne
    0.42
     it
    0.42
    Activations Density 0.000%

    No Known Activations