© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 41093
    Prev
    Next
    INDEX
    Explanations

    recognize pseudo or slower speeds

    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
    initial
    0.52
    lowest
    0.46
    current
    0.43
     ผ
    0.42
    new
    0.42
    staff
    0.42
    ation
    0.41
     succeeding
    0.41
    sample
    0.40
    void
    0.40
    POSITIVE LOGITS
    चारिक
    0.46
     drank
    0.43
    ेटिक
    0.42
     sporadic
    0.42
    ྃ
    0.41
     competitor
    0.40
    ርት
    0.40
     demás
    0.40
    ISTIC
    0.40
    Открыть
    0.39
    Activations Density 0.008%

    No Known Activations