© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    coding assistants

    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
    나
    0.93
    на
    0.90
    ی
    0.84
     replete
    0.84
    র
    0.84
    ের
    0.79
     sogen
    0.77
     recognize
    0.77
    ಾನ್
    0.76
    다
    0.76
    POSITIVE LOGITS
    ton
    1.15
    -
    1.13
    redients
    1.11
    <0xA3>
    1.03
    ting
    0.91
    a
    0.85
     a
    0.82
    ly
    0.79
    oa
    0.79
    +
    0.77
    Activations Density 0.493%

    No Known Activations