© 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-262K
    7. 38810
    Prev
    Next
    INDEX
    Explanations

    Attention and repetition systems

    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_262k_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
     cree
    0.44
     simpat
    0.41
     creep
    0.41
    云
    0.39
     przew
    0.38
     sư
    0.38
    Rank
    0.38
    &&
    0.38
    ƾ
    0.38
    WEST
    0.37
    POSITIVE LOGITS
     chargingStation
    0.52
    roda
    0.51
     ዋና
    0.50
    𝐒
    0.48
    🛖
    0.47
    utim
    0.46
    管理器
    0.45
    都要
    0.44
    atat
    0.44
    ेंशियल
    0.44
    Activations Density 0.009%

    No Known Activations