© 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. 74234
    Prev
    Next
    INDEX
    Explanations

    vote to legalize

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

    principles, benefits, or explanations

    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
    i
    0.52
    o
    0.49
     computational
    0.45
    t
    0.44
    x
    0.44
    by
    0.44
    in
    0.44
    istica
    0.43
     πε
    0.42
     логи
    0.42
    POSITIVE LOGITS
    ല്ലാം
    0.45
    ancienne
    0.45
     Autres
    0.44
     Otro
    0.43
    Ố
    0.43
     Анаста
    0.42
     Cũng
    0.42
     בת
    0.42
     nạn
    0.41
     sospe
    0.41
    Activations Density 0.001%

    No Known Activations