© 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. 76462
    Prev
    Next
    INDEX
    Explanations

    questions about, deep breath

    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
     Б
    0.44
     Хар
    0.38
     и
    0.38
     ولكن
    0.37
     ([
    0.37
    Entire
    0.37
     sounded
    0.37
     хар
    0.36
     Certains
    0.36
    實際上
    0.36
    POSITIVE LOGITS
    uestra
    0.47
    y
    0.46
     ATV
    0.45
    anaconda
    0.44
     Chihuahua
    0.44
    wwww
    0.44
    aco
    0.42
    ebug
    0.42
    ndvi
    0.42
     leisurely
    0.42
    Activations Density 0.003%

    No Known Activations