© 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. 159303
    Prev
    Next
    INDEX
    Explanations

    unmistakable personality

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

    lists or choices

    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
    鏻
    0.50
     onChange
    0.49
     Redox
    0.49
    权重
    0.47
    应对
    0.46
     Genomics
    0.46
    黝
    0.46
    铌
    0.46
     firef
    0.46
     arbete
    0.45
    POSITIVE LOGITS
    typical
    0.58
    dict
    0.56
    such
    0.52
    或
    0.52
     or
    0.52
    daftar
    0.49
    したり
    0.49
    하거나
    0.49
    return
    0.49
    common
    0.49
    Activations Density 0.000%

    No Known Activations