© 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. 194250
    Prev
    Next
    INDEX
    Explanations

    preceded by an event

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

    combining and requiring carefulness

    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
    ics
    0.45
     Arkansas
    0.44
     Am
    0.44
     눌
    0.44
     Lookout
    0.44
     Answers
    0.44
     മേ
    0.43
     જોવા
    0.43
     மே
    0.43
     미
    0.42
    POSITIVE LOGITS
     procédé
    0.47
     dịp
    0.47
     preceded
    0.46
    тік
    0.46
     ondernem
    0.45
    artige
    0.45
    peptide
    0.45
     cordon
    0.44
     stroked
    0.44
     trafik
    0.44
    Activations Density 0.000%

    No Known Activations