© 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. 20543
    Prev
    Next
    INDEX
    Explanations

    . imperial, After, U, s, model, age

    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
     احمد
    0.39
     ಮತ್ತೆ
    0.39
    nte
    0.38
    mmmm
    0.37
    gettags
    0.36
    जीत
    0.35
    ຣ
    0.35
     دوبارہ
    0.35
    婫
    0.35
    偒
    0.34
    POSITIVE LOGITS
     This
    0.38
     Thorough
    0.37
     Artillery
    0.37
     Raster
    0.35
     Universe
    0.34
     In
    0.34
     Example
    0.34
    L
    0.34
     These
    0.34
     P
    0.34
    Activations Density 0.002%

    No Known Activations