© 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. 105456
    Prev
    Next
    INDEX
    Explanations

    "I do" or "she was"

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

    purpose and specialized tasks

    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
    ing
    0.53
    seated
    0.52
    sup
    0.50
    rural
    0.49
    ord
    0.49
    irthday
    0.48
    %-
    0.47
    asper
    0.47
    uh
    0.46
    andre
    0.46
    POSITIVE LOGITS
    球员
    0.54
    மன்
    0.49
    缺陷
    0.49
    样品
    0.48
     sổ
    0.48
    蒴
    0.48
     función
    0.47
    错误
    0.47
    电信
    0.47
    锥
    0.47
    Activations Density 0.000%

    No Known Activations