© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    code block syntax

    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
    ের
    0.28
    يف
    0.27
     eddies
    0.26
     అనేది
    0.26
    」。
    0.25
    ARIA
    0.25
     acha
    0.25
    ]।
    0.25
    ARB
    0.24
    ANE
    0.24
    POSITIVE LOGITS
    ierende
    0.28
    த்துக்
    0.26
     Destruction
    0.25
    ຮ
    0.25
    opherol
    0.24
    hij
    0.24
    прочем
    0.24
     काढून
    0.24
    etter
    0.24
    وأضاف
    0.23
    Activations Density 0.360%

    No Known Activations