© 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. 2375
    Prev
    Next
    INDEX
    Explanations

    significant events or states

    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
     slightly
    0.52
     või
    0.52
    或其他
    0.51
     somewhat
    0.48
     মোটামুটি
    0.47
    （
    0.46
    特色的
    0.46
    /
    0.45
     from
    0.45
     কিছুটা
    0.45
    POSITIVE LOGITS
     และ
    0.69
    ؛
    0.60
     અને
    0.60
    。『
    0.60
     और
    0.59
    했고
    0.58
    。「
    0.57
    。
    0.57
    .
    0.56
    ۔
    0.56
    Activations Density 0.309%

    No Known Activations