© 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. 28359
    Prev
    Next
    INDEX
    Explanations

    raising rates

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

    quotes or specific content

    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
    பால்
    0.46
     सकुशल
    0.44
    酴
    0.43
     menggunakan
    0.43
    --------------
    0.43
     AUTO
    0.43
    atanga
    0.43
    ाराम
    0.42
    麸
    0.42
    ubble
    0.42
    POSITIVE LOGITS
     някои
    0.46
     někter
    0.45
     consid
    0.45
     dollars
    0.44
     algunos
    0.44
     ብዙውን
    0.44
     hexagons
    0.43
     varier
    0.43
     distorted
    0.43
     některé
    0.42
    Activations Density 0.000%

    No Known Activations