© 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. 5959
    Prev
    Next
    INDEX
    Explanations

    headings for descriptions

    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
    تن
    0.50
    们的
    0.48
    VEN
    0.47
    out
    0.46
    ים
    0.45
    ์
    0.44
    NSNumber
    0.44
    time
    0.43
    ่า
    0.43
    ি
    0.43
    POSITIVE LOGITS
     estilo
    0.60
     khas
    0.53
     बदलकर
    0.52
    গত
    0.51
     тип
    0.51
     của
    0.51
     도와
    0.51
     formato
    0.50
     antidepressant
    0.50
     semelhante
    0.50
    Activations Density 0.250%

    No Known Activations