© 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. 183016
    Prev
    Next
    INDEX
    Explanations

    academic terms and technical descriptions

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

    life stages and demographics

    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
     direction
    0.56
    Le
    0.55
     Communications
    0.55
    C
    0.54
     server
    0.53
    S
    0.53
    F
    0.52
    Sp
    0.52
     control
    0.51
    G
    0.50
    POSITIVE LOGITS
     вашем
    0.57
    合わせて
    0.56
     என்ற
    0.55
    userDetails
    0.55
     அ
    0.54
    lensFlare
    0.54
    favourites
    0.54
    ವಾಗಿರುತ್ತದೆ
    0.52
     ин
    0.52
    removeFrom
    0.52
    Activations Density 0.000%

    No Known Activations