© 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. 88656
    Prev
    Next
    INDEX
    Explanations

    day care, storage in, artist in

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

    valuable insights and potential

    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
    ЗО
    0.52
    й
    0.51
    рая
    0.47
     ราศี
    0.46
     많이
    0.45
     वृंदा
    0.45
    Т
    0.42
    ໕
    0.42
    ОР
    0.42
    mediately
    0.42
    POSITIVE LOGITS
     میوز
    0.46
    ၈
    0.45
    edged
    0.44
    樓
    0.43
    queued
    0.43
     necessary
    0.42
    percentage
    0.42
     attributed
    0.42
     sculpture
    0.42
     conferred
    0.42
    Activations Density 0.000%

    No Known Activations