© 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. 41415
    Prev
    Next
    INDEX
    Explanations

    completing actions or sequences

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

    real or actual

    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
    A
    0.58
    B
    0.49
    Enabled
    0.48
    Families
    0.46
    UserId
    0.46
    Categories
    0.46
    Current
    0.45
    Available
    0.45
     para
    0.45
    ڑا
    0.45
    POSITIVE LOGITS
     மெ
    0.49
     реаль
    0.49
     чыныгы
    0.47
     書
    0.46
     메
    0.46
     задачи
    0.46
    hiq
    0.46
     ಮತ್ತ
    0.45
     どう
    0.45
    ])
    0.44
    Activations Density 0.000%

    No Known Activations