© 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. 219838
    Prev
    Next
    INDEX
    Explanations

    installing and first steps

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

    technical descriptions

    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
    xas
    0.51
     you
    0.49
    o
    0.49
     v
    0.49
    Y
    0.46
    ם
    0.46
    th
    0.46
    yen
    0.46
     э
    0.45
    b
    0.45
    POSITIVE LOGITS
    قيقي
    0.53
    Пред
    0.50
    они
    0.50
    чиков
    0.49
    Mét
    0.49
    гона
    0.48
    秥
    0.48
    ించిన
    0.47
    Samantha
    0.47
    ում
    0.47
    Activations Density 0.000%

    No Known Activations