© 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. 185466
    Prev
    Next
    INDEX
    Explanations

    from Foundation, fundamental doctrines

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

    torque, yourself, rapidly, some, fuse

    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
    Negative Logits
     dharma
    0.55
     কর্মকর্তা
    0.53
     孔
    0.52
     하늘
    0.52
    孔
    0.50
     bhikkh
    0.49
     steamed
    0.48
    ลม
    0.48
     разделить
    0.48
     líderes
    0.46
    POSITIVE LOGITS
    ظ
    0.50
    ತಕ್ಕ
    0.47
    po
    0.47
    να
    0.46
    cA
    0.46
    ital
    0.45
     negocio
    0.44
    </body>
    0.44
    $+
    0.43
    ifestyles
    0.43
    Activations Density 0.000%

    No Known Activations