© 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. 180448
    Prev
    Next
    INDEX
    Explanations

    milk, desk, rating

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

    question marks

    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
     mercado
    0.48
    orce
    0.47
     guerrilla
    0.40
     맥
    0.40
     Mercado
    0.40
     malicious
    0.40
     covenant
    0.40
    භ
    0.40
     waterproof
    0.40
    Sections
    0.40
    POSITIVE LOGITS
    <h4>
    0.48
    а
    0.46
     особенностей
    0.46
     HAN
    0.46
    中
    0.46
     SISO
    0.44
     SCAN
    0.44
     JIM
    0.43
    这点
    0.42
     бло
    0.42
    Activations Density 0.000%

    No Known Activations