© 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. 112944
    Prev
    Next
    INDEX
    Explanations

    Surcle

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

    multiple choice answers

    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
    ગુ
    0.52
    Asked
    0.50
    茁
    0.47
    ﺪ
    0.47
    Jurassic
    0.47
    وسع
    0.47
    Period
    0.47
    翱
    0.46
    Moving
    0.46
    经典
    0.46
    POSITIVE LOGITS
     poems
    0.46
    china
    0.45
     doughnuts
    0.44
     muted
    0.44
     peaceful
    0.44
     salads
    0.44
     homogeneity
    0.43
     yoghurt
    0.43
     চীন
    0.42
     darkened
    0.42
    Activations Density 0.000%

    No Known Activations