© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199243
    Prev
    Next
    INDEX
    Explanations

    ending lineup

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

    diverse communities and specific laws

    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
    Negative Logits
    亚马
    0.50
    immune
    0.50
    pyrazine
    0.49
    diethyl
    0.49
    肿
    0.48
    catering
    0.47
    pyrazin
    0.46
    RUTA
    0.46
    diamine
    0.46
    pyrazole
    0.46
    POSITIVE LOGITS
    ক
    0.49
     ۲
    0.46
     č
    0.45
    ………
    0.45
     Examination
    0.44
     Explo
    0.44
     Begriff
    0.44
     UP
    0.44
    𝒔
    0.44
     alia
    0.43
    Activations Density 0.001%

    No Known Activations