© 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-65K
    7. 8089
    Prev
    Next
    INDEX
    Explanations

    certain aspects

    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_65k_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
    Binary
    0.48
    การ
    0.47
    0.47
     phylogenetic
    0.45
     attorney
    0.45
     ese
    0.44
    ད
    0.44
     periods
    0.44
    abu
    0.44
     related
    0.42
    POSITIVE LOGITS
    panelMenuList
    0.54
     ਕੀਤਾ
    0.50
    되면
    0.49
    ोजित
    0.48
    gaxModule
    0.46
    reflectionMap
    0.45
    츰
    0.45
    <bbox>
    0.45
     স্ন
    0.45
    <unused557>
    0.45
    Activations Density 0.012%

    No Known Activations