© 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. 127559
    Prev
    Next
    INDEX
    Explanations

    listening, idea, still, reading, tempted

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

    vastly more

    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
    $',
    0.55
     電気
    0.55
    $\\
    0.52
     zemlji
    0.52
    //$
    0.51
     independente
    0.51
    ":"
    0.50
     कामका
    0.50
    ]',
    0.49
     travaux
    0.49
    POSITIVE LOGITS
    谘
    0.53
    ipramine
    0.44
    وازن
    0.41
    重大
    0.41
    ABA
    0.40
    ipennis
    0.40
     cheat
    0.39
    知的
    0.39
    徹底
    0.39
    織
    0.39
    Activations Density 0.000%

    No Known Activations