© 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. 129578
    Prev
    Next
    INDEX
    Explanations

    continues after list item

    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
    (!)
    0.14
    Benzyloxy
    0.14
    ᑖ
    0.14
    득
    0.13
     (!)
    0.13
    리의
    0.13
    웬
    0.13
    兴
    0.13
    장의
    0.13
    랍
    0.13
    POSITIVE LOGITS
    चानक
    0.16
    kit
    0.16
    and
    0.15
    soft
    0.15
    gfx
    0.15
    tib
    0.15
    for
    0.15
    it
    0.15
    uk
    0.15
    hj
    0.15
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.