© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    bar charts and graphs

    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
    ש
    0.64
    Во
    0.63
    Destroy
    0.60
    其他
    0.58
    Про
    0.57
    Yeni
    0.56
    Ни
    0.56
    Juventus
    0.56
    Д
    0.56
    ﹡
    0.56
    POSITIVE LOGITS
     bar
    0.80
     bars
    0.76
    bar
    0.75
     Bar
    0.69
     barra
    0.65
     Bars
    0.64
    abar
    0.59
     بار
    0.59
     barras
    0.59
    bars
    0.59
    Activations Density 0.034%

    No Known Activations