© 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. 252935
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    سك
    0.45
    obst
    0.44
    {$
    0.43
    تبه
    0.43
    aporte
    0.43
    itus
    0.42
    کند
    0.42
     relato
    0.42
     velho
    0.41
    大使
    0.41
    POSITIVE LOGITS
     从
    0.63
     对
    0.59
     通过
    0.57
     选择
    0.57
     专业
    0.54
     Methyl
    0.52
     参数
    0.52
    从
    0.52
     イベント
    0.52
     赵
    0.52
    Activations Density 0.002%

    No Known Activations