© 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. 125443
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    organized structure

    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
    르면
    0.48
    fulfill
    0.48
    ويس
    0.48
    pulumi
    0.48
    pmatrix
    0.47
    얏
    0.46
    لم
    0.46
    divisor
    0.46
    لیس
    0.46
    يت
    0.45
    POSITIVE LOGITS
    ariously
    0.54
     Lie
    0.48
     Literary
    0.47
     Nome
    0.47
     fuer
    0.46
    asyonu
    0.45
     Caution
    0.45
     ഉണ്ട്
    0.44
     ‘
    0.44
     wrong
    0.44
    Activations Density 0.000%

    No Known Activations