© 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. 86242
    Prev
    Next
    INDEX
    Explanations

    names of people and places

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

    ways to expand or complete

    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
     ilus
    0.48
    らない
    0.47
    कंप
    0.46
    酣
    0.46
    ᄅ
    0.46
    恍
    0.46
     vrchol
    0.45
    époque
    0.45
    समय
    0.45
    ј
    0.45
    POSITIVE LOGITS
     cannabinoids
    0.42
    uran
    0.42
     ওসমান
    0.41
    நாதன்
    0.41
    II
    0.40
     Brooke
    0.39
     Police
    0.39
    ITTER
    0.39
     IONS
    0.38
     investigators
    0.38
    Activations Density 0.002%

    No Known Activations