© 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. 21710
    Prev
    Next
    INDEX
    Explanations

    inequalities and mastery

    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
     gripped
    0.54
    Votre
    0.44
    鬍
    0.44
     थीं
    0.43
    زيز
    0.43
    <!
    0.42
     volition
    0.42
     coated
    0.41
     nettement
    0.41
    Појединачна
    0.41
    POSITIVE LOGITS
    نان
    0.45
    മുള്ള
    0.45
     Hastings
    0.44
     Steck
    0.42
    lass
    0.42
     እና
    0.41
     (`
    0.41
     L
    0.40
    acute
    0.38
     สําหรับ
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.