Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52813
    Prev
    Next
    INDEX
    Explanations

    ranges and practices

    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
     Bison
    0.54
    optera
    0.51
    理工
    0.49
    ス
    0.48
     afuera
    0.46
     veldig
    0.46
    unna
    0.45
     ゆっくり
    0.44
    ramiento
    0.44
     idealism
    0.44
    POSITIVE LOGITS
     at
    0.58
     combined
    0.56
     general
    0.53
    h
    0.52
     make
    0.52
     have
    0.51
     new
    0.51
     diff
    0.51
     water
    0.49
     coated
    0.48
    Activations Density 0.002%

    No Known Activations