© 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. 239299
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and technical descriptions

    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
     paese
    0.46
     pero
    0.45
    %.
    0.43
     hasn
    0.43
     havent
    0.43
     player
    0.43
    **/
    0.42
    除非
    0.42
    મો
    0.42
     can
    0.42
    POSITIVE LOGITS
     २४
    0.56
    ólnie
    0.53
     გახ
    0.50
     돌
    0.48
     ८
    0.48
     preface
    0.47
    gage
    0.46
    elang
    0.46
     anguish
    0.45
     त्र
    0.45
    Activations Density 0.000%

    No Known Activations