© 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. 59907
    Prev
    Next
    INDEX
    Explanations

    verb phrases and participants

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

    current and previous states

    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
    沇
    0.51
    Items
    0.50
    सेक्स
    0.50
    Combin
    0.50
    Produ
    0.49
    Normally
    0.49
    ToRemove
    0.49
    utérus
    0.48
    Analysts
    0.48
    Capabilities
    0.48
    POSITIVE LOGITS
     humiliated
    0.59
     the
    0.58
     F
    0.57
     brought
    0.54
     Shanghai
    0.54
     oil
    0.53
     Hokkaido
    0.53
     Greenland
    0.52
     h
    0.52
     Zealand
    0.52
    Activations Density 0.000%

    No Known Activations