© 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. 210206
    Prev
    Next
    INDEX
    Explanations

    enterprise resources

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

    however, this support

    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
     G
    0.55
    arning
    0.53
    5
    0.52
     Risk
    0.52
     B
    0.50
     Heart
    0.50
     Universities
    0.49
     Jean
    0.49
     C
    0.49
     RG
    0.49
    POSITIVE LOGITS
     opér
    0.56
    льбе
    0.54
     rétr
    0.54
     längst
    0.51
     ombil
    0.51
     órg
    0.51
     ôm
    0.50
     oś
    0.50
     hyperlocal
    0.50
     اولم
    0.50
    Activations Density 0.000%

    No Known Activations