© 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. 84057
    Prev
    Next
    INDEX
    Explanations

    obsolete, Haley, license, cannot, cancel

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

    language used, harmless virus, traditional AMD

    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
    G
    0.53
    D
    0.50
    H
    0.45
    ok
    0.45
     ensures
    0.45
    R
    0.45
    dicke
    0.44
    K
    0.44
    이
    0.44
    V
    0.44
    POSITIVE LOGITS
     انکار
    0.43
     unele
    0.40
     μέχρι
    0.40
     classi
    0.40
     witty
    0.38
     بابەت
    0.38
     indeterm
    0.38
     incluindo
    0.37
     rôle
    0.37
     niektórych
    0.37
    Activations Density 0.001%

    No Known Activations