© 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. 5559
    Prev
    Next
    INDEX
    Explanations

    collection, collections

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

    collections

    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
     terbang
    0.45
    칫
    0.43
    ɻ
    0.43
    月底
    0.41
    Derivative
    0.40
    坨
    0.37
    resión
    0.37
    륵
    0.36
     جذر
    0.36
    aitan
    0.36
    POSITIVE LOGITS
     Collections
    0.81
     Coll
    0.80
     Colle
    0.80
     COLLE
    0.80
     коллек
    0.78
     Collect
    0.77
     Collection
    0.77
     coll
    0.76
     Kole
    0.75
     colle
    0.74
    Activations Density 0.028%

    No Known Activations