© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 65252
    Prev
    Next
    INDEX
    Explanations

    Domain, Range, code structure

    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
    from
    0.54
    if
    0.53
    one
    0.52
    info
    0.51
    with
    0.51
    8
    0.50
    0
    0.48
     best
    0.48
    2
    0.48
    9
    0.48
    POSITIVE LOGITS
    ㎛
    0.45
     Franti
    0.45
     Česk
    0.45
     của
    0.44
     obiekt
    0.43
     მი
    0.43
     chùa
    0.43
     UWGM
    0.42
     njima
    0.42
     njih
    0.42
    Activations Density 0.071%

    No Known Activations