© 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. 31416
    Prev
    Next
    INDEX
    Explanations

    describes figures

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

    views, schematics, and diagrams

    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
     cAMP
    0.49
     CpG
    0.43
    hydration
    0.42
    geq
    0.41
    multicol
    0.40
     therapies
    0.39
     ({\
    0.38
    atosis
    0.38
     სპ
    0.38
    削減
    0.38
    POSITIVE LOGITS
    还没
    0.49
     अधूरा
    0.45
     entender
    0.44
    ristmas
    0.43
    Tal
    0.42
    Illust
    0.42
    Ｘ
    0.41
    Simplified
    0.41
     pencil
    0.41
     üt
    0.40
    Activations Density 0.019%

    No Known Activations