© 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. 48802
    Prev
    Next
    INDEX
    Explanations

    Assumes roles or describes people, places, or versions

    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
     <<"
    0.49
     podido
    0.46
    ra
    0.46
    ard
    0.45
    ँची
    0.44
    ించాడు
    0.43
    offe
    0.43
    oy
    0.43
    weist
    0.43
    adillo
    0.43
    POSITIVE LOGITS
    s
    0.62
    できる
    0.59
    我們
    0.57
    с
    0.55
    、
    0.53
    There
    0.52
    ين
    0.52
    いる
    0.51
    ي
    0.51
     courtes
    0.50
    Activations Density 0.046%

    No Known Activations