© 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. 178660
    Prev
    Next
    INDEX
    Explanations

    owner feels, known fact, proceed east

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

    cellular senescence, subtle yet

    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
     الدراسة
    0.49
    উন্ট
    0.47
    ِين
    0.46
    ريف
    0.44
     parque
    0.44
     pequenas
    0.44
     للنساء
    0.44
     ਡ
    0.43
    nac
    0.43
    izielle
    0.43
    POSITIVE LOGITS
     February
    0.47
    MO
    0.46
    の
    0.45
    testimonial
    0.45
    ’
    0.44
    AX
    0.43
     bank
    0.43
     chiamato
    0.42
     to
    0.42
     virtual
    0.42
    Activations Density 0.000%

    No Known Activations