© 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. 201856
    Prev
    Next
    INDEX
    Explanations

    available seven, for every, protecting incredible, short stories, influential

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

    Pilot:Target resultseen civilizationscomprehendingmodify the

    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
    läge
    0.50
     อี
    0.49
    [,,"
    0.48
    FANG
    0.47
    sang
    0.46
    asang
    0.46
    秏
    0.46
    Constructor
    0.46
    㔯
    0.45
     ات
    0.45
    POSITIVE LOGITS
     ability
    0.48
     a
    0.46
    -
    0.46
    ргани
    0.46
     spectral
    0.46
     quanto
    0.45
     sobre
    0.44
     reprez
    0.44
     weathered
    0.44
     comparatively
    0.44
    Activations Density 0.000%

    No Known Activations