© 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. 12702
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
    be
    0.66
    ir
    0.63
    it
    0.62
    ur
    0.57
    i
    0.57
    te
    0.56
    EN
    0.56
    oa
    0.54
    ו
    0.54
    is
    0.52
    POSITIVE LOGITS
     작동
    0.76
     механиз
    0.71
     funcionan
    0.71
     fonctionnent
    0.70
    仕組み
    0.66
     funciona
    0.66
     mecanismo
    0.65
     mechanisms
    0.64
     mecanismos
    0.64
     mekanisme
    0.63
    Activations Density 0.087%

    No Known Activations