© 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. 27993
    Prev
    Next
    INDEX
    Explanations

    schedule, log, Article, individuals

    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
    枒
    0.52
     Agriculture
    0.46
    杓
    0.44
     ITS
    0.44
     Batteries
    0.44
    暘
    0.43
    庭
    0.43
    竻
    0.43
    挣
    0.43
     "¿
    0.42
    POSITIVE LOGITS
    ali
    0.59
    utas
    0.56
    al
    0.55
    can
    0.54
    ar
    0.53
    ry
    0.52
    up
    0.51
    ate
    0.50
    av
    0.50
    un
    0.50
    Activations Density 0.003%

    No Known Activations