© 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. 71832
    Prev
    Next
    INDEX
    Explanations

    Part IV

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

    fruit basket

    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
    ح
    0.46
    مم
    0.44
     :=
    0.44
    y
    0.44
    PRODUCT
    0.44
    ال
    0.43
    Cox
    0.42
    phas
    0.41
     U
    0.40
     Whale
    0.39
    POSITIVE LOGITS
    рили
    0.56
     ganglions
    0.55
    点で
    0.54
     λέ
    0.50
    ését
    0.50
    間で
    0.49
     маль
    0.49
     앞에서
    0.49
     Compre
    0.48
    ところで
    0.48
    Activations Density 0.000%

    No Known Activations