© 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. 216329
    Prev
    Next
    INDEX
    Explanations

    lifestyle television

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

    inferred from reasons

    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
    墾
    0.45
     Ib
    0.44
    ቓ
    0.44
     Crossed
    0.44
    绅
    0.44
    壹
    0.44
     Edd
    0.43
    ों
    0.43
    静
    0.43
    ต่าง
    0.43
    POSITIVE LOGITS
     maar
    0.49
     baina
    0.44
    );
    0.44
    ections
    0.44
    cienza
    0.44
     পুষ্প
    0.44
    opathy
    0.43
     zunächst
    0.43
    asketball
    0.43
    ropathy
    0.43
    Activations Density 0.001%

    No Known Activations