© 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. 91204
    Prev
    Next
    INDEX
    Explanations

    cylinder head

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

    learning, self-awareness, desire, trends

    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
     Eastwood
    0.44
     haar
    0.43
     breathe
    0.42
    ffer
    0.41
    $)$.
    0.41
    th
    0.41
     டாக
    0.41
    वरण
    0.40
    ตรง
    0.39
     ไม
    0.39
    POSITIVE LOGITS
     eller
    0.52
     ہوئی
    0.52
    ські
    0.50
     señ
    0.49
    或
    0.48
    ших
    0.47
     piens
    0.46
     superconduct
    0.46
     conducción
    0.46
    ಣ
    0.46
    Activations Density 0.000%

    No Known Activations