© 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. 177268
    Prev
    Next
    INDEX
    Explanations

    setting up actions

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

    pay monthly subscriptions

    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
    Мак
    0.50
    Keller
    0.47
     erlaub
    0.47
    嘏
    0.47
    騇
    0.46
    коло
    0.46
    듈
    0.46
    갠
    0.46
    㳯
    0.46
    colon
    0.45
    POSITIVE LOGITS
     printed
    0.49
     pés
    0.48
     অস্থায়ী
    0.45
     tedious
    0.43
     significativa
    0.43
     thickened
    0.43
     I
    0.43
     reflected
    0.43
     redirected
    0.43
     ö
    0.42
    Activations Density 0.002%

    No Known Activations