© 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. 10854
    Prev
    Next
    INDEX
    Explanations

    authentication credentials

    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
    s
    0.68
    B
    0.52
    re
    0.50
    r
    0.50
    govor
    0.50
    tid
    0.49
    ra
    0.48
    j
    0.48
    t
    0.48
    nt
    0.46
    POSITIVE LOGITS
    $).
    0.49
    мережа
    0.48
    テンツ
    0.46
    ികിത്സ
    0.46
    選手
    0.45
     سپورټ
    0.44
     sürec
    0.44
     julio
    0.44
    _);
    0.44
     campeonato
    0.43
    Activations Density 0.014%

    No Known Activations