© 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. 158663
    Prev
    Next
    INDEX
    Explanations

    listing, highest, controls, players

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

    disrupt essential online services

    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
     handbags
    0.49
     emptied
    0.45
    ating
    0.44
    ateur
    0.44
     resigned
    0.43
     handbag
    0.43
     ਹ
    0.42
    logged
    0.42
    ience
    0.41
    ClassObject
    0.41
    POSITIVE LOGITS
     Grunge
    0.50
     Risks
    0.50
     कुर्बानी
    0.48
    栩
    0.47
     Ris
    0.47
    व्ही
    0.47
     CANVAS
    0.47
     Credits
    0.47
     Notices
    0.46
    LIFE
    0.46
    Activations Density 0.000%

    No Known Activations