© 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. 834
    Prev
    Next
    INDEX
    Explanations

    education, international affairs, science, multilingual

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

    medical, scientific, and technical review titles

    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
    ซ
    0.45
    ↵↵
    0.41
    Па
    0.41
    લ્સ
    0.41
     zeich
    0.41
    plik
    0.40
     ซ
    0.40
    લ્
    0.39
    platte
    0.38
    hstack
    0.38
    POSITIVE LOGITS
     EDUCATION
    0.45
     działalności
    0.44
    ործ
    0.44
    颍
    0.43
     pandemics
    0.42
     аспек
    0.41
     образова
    0.41
     코로나
    0.40
     অনেকেই
    0.39
    EDUCATION
    0.39
    Activations Density 0.001%

    No Known Activations