© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101437
    Prev
    Next
    INDEX
    Explanations

    part of a group

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

    gas station, critical, true, crucial

    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
    F
    0.58
    W
    0.57
    H
    0.53
    X
    0.53
    U
    0.53
    WK
    0.50
    N
    0.50
    xadmin
    0.49
    V
    0.49
    Ll
    0.49
    POSITIVE LOGITS
     divergents
    0.56
     epiph
    0.51
     diverg
    0.50
     bipart
    0.49
     diverging
    0.47
     degrés
    0.47
     vigilance
    0.47
     これは
    0.46
     convivial
    0.46
     divergent
    0.46
    Activations Density 0.000%

    No Known Activations