© 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. 154245
    Prev
    Next
    INDEX
    Explanations

    utility services and bills

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

    surprise, fear, focus

    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
    تالي
    0.48
     Unterschiede
    0.48
    ura
    0.47
     rumors
    0.46
     Policies
    0.45
    ata
    0.45
    辈
    0.45
     Italians
    0.44
     rêves
    0.44
     Titles
    0.43
    POSITIVE LOGITS
    Ding
    0.50
     feeder
    0.47
    ፈለ
    0.47
    すぐに
    0.46
    Erd
    0.44
     inspect
    0.43
    querdo
    0.43
    intercept
    0.42
    Blank
    0.42
     ಖ
    0.42
    Activations Density 0.000%

    No Known Activations