© 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. 174150
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    Chorus and exclamation marks

    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
     Lesser
    0.52
     cận
    0.52
     Hyatt
    0.48
     Maret
    0.47
     बचे
    0.47
    အတွက်
    0.45
     store
    0.45
    蕭
    0.45
    軻
    0.45
    بيب
    0.44
    POSITIVE LOGITS
    if
    0.53
    aa
    0.45
    フィルム
    0.45
    đ
    0.45
    酊
    0.45
    Após
    0.44
    Maar
    0.43
    Después
    0.42
    Trên
    0.42
    producing
    0.42
    Activations Density 0.001%

    No Known Activations