© 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. 205022
    Prev
    Next
    INDEX
    Explanations

    completely, blind, erased, lakes

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

    Copilot Pro

    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
     인해
    0.54
     descendant
    0.54
     beni
    0.52
     comod
    0.51
     discarded
    0.51
     descendants
    0.50
    ಂಡ್
    0.50
     (+)
    0.50
     почув
    0.50
    ﱠ
    0.50
    POSITIVE LOGITS
    Water
    0.48
    ài
    0.47
    doi
    0.47
     Water
    0.47
    ug
    0.46
    Mutual
    0.45
    ual
    0.44
    team
    0.44
    队的
    0.44
    队
    0.44
    Activations Density 0.001%

    No Known Activations