© 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. 15059
    Prev
    Next
    INDEX
    Explanations

    our planet

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

    police arrive

    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
    п
    0.55
    长
    0.54
    压缩
    0.53
    νά
    0.53
    锂
    0.51
    Ба
    0.50
    et
    0.50
    longmapsto
    0.48
    张
    0.48
    Пі
    0.47
    POSITIVE LOGITS
     vain
    0.48
    vain
    0.46
     विरुद्ध
    0.44
     Byrd
    0.44
     warrantless
    0.42
    usive
    0.42
    ým
    0.41
     menjaga
    0.41
     While
    0.41
    lords
    0.41
    Activations Density 0.000%

    No Known Activations