© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    code or special characters

    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
    illiams
    0.52
    _
    0.52
     precursors
    0.50
    5
    0.50
    4
    0.49
     molds
    0.48
    ¼
    0.47
    bit
    0.47
    layout
    0.46
    launcher
    0.46
    POSITIVE LOGITS
    蘄
    0.51
     perse
    0.50
     Plac
    0.49
     richi
    0.47
    読んで
    0.46
     tetapi
    0.46
     poderá
    0.46
     Canva
    0.46
    滹
    0.46
     लिप
    0.45
    Activations Density 0.001%

    No Known Activations