© 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. 62741
    Prev
    Next
    INDEX
    Explanations

    Mount Hamilton

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

    talking about family history or science concepts

    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
    <0x80>
    0.47
    aw
    0.47
     appeals
    0.46
     chambers
    0.46
    з
    0.46
    pounds
    0.45
    ही
    0.44
    ни
    0.44
    w
    0.44
    &
    0.44
    POSITIVE LOGITS
     Beiträge
    0.57
     Gemä
    0.54
     Quân
    0.54
     Método
    0.53
     Aufnahme
    0.52
     Constraint
    0.52
     Commencez
    0.52
     Normalmente
    0.51
     Catalogue
    0.50
     Função
    0.50
    Activations Density 0.000%

    No Known Activations