© 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. 153599
    Prev
    Next
    INDEX
    Explanations

    connection or relationship descriptors

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

    potential energy spin

    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
     moz
    0.47
     Algunos
    0.46
     Chromebook
    0.46
     Pfl
    0.46
     conforms
    0.46
     P
    0.45
     anonym
    0.45
     salida
    0.44
    杯
    0.44
     Polyg
    0.44
    POSITIVE LOGITS
    hubungan
    0.54
    assertEquals
    0.53
    lombok
    0.50
    onRouteChange
    0.50
    Nguyen
    0.46
     નિર્ણય
    0.45
     যাত্র
    0.44
    Nhap
    0.44
     Yên
    0.44
    িদ্ধ
    0.43
    Activations Density 0.001%

    No Known Activations