© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 54607
    Prev
    Next
    INDEX
    Explanations

    writing

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

    data governance or tools

    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
     kuwa
    0.56
    ੀ
    0.52
     buildFor
    0.48
     béné
    0.47
    USERNAME
    0.46
     datang
    0.46
     conserved
    0.45
     pukul
    0.45
    DELETE
    0.45
     ikut
    0.44
    POSITIVE LOGITS
     Bollinger
    0.52
     Accom
    0.49
     ఖ
    0.47
     Laf
    0.47
     McCain
    0.47
     Mann
    0.46
    gten
    0.46
     Institutes
    0.45
    玨
    0.45
     selections
    0.44
    Activations Density 0.000%

    No Known Activations