© 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. 177092
    Prev
    Next
    INDEX
    Explanations

    related to blushing or violations

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

    given the

    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
     મળે
    0.50
     влияние
    0.47
     निकली
    0.47
    tre
    0.47
     পেন
    0.47
     ripple
    0.45
    Ꮑ
    0.44
    нике
    0.44
     ď
    0.44
    </h2>
    0.43
    POSITIVE LOGITS
     OEMs
    0.55
     Soviets
    0.53
    Пра
    0.53
     icons
    0.52
    మన్
    0.49
     équipes
    0.49
     예정
    0.49
    права
    0.48
     décisions
    0.47
     isValid
    0.47
    Activations Density 0.000%

    No Known Activations