© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33037
    Prev
    Next
    INDEX
    Explanations

    available methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [,,"
    0.48
    Portada
    0.47
    tFileInputExcel
    0.47
     risque
    0.44
    versible
    0.43
    impose
    0.43
    ковь
    0.43
    漅
    0.43
    Notas
    0.42
     penis
    0.42
    POSITIVE LOGITS
     Sie
    0.50
     Sensing
    0.49
     Oct
    0.47
     wodurch
    0.47
     artikkel
    0.46
    ی
    0.44
     octombrie
    0.44
    ות
    0.44
     Turned
    0.43
    oarthritis
    0.43
    Activations Density 0.003%

    No Known Activations