© 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. 27557
    Prev
    Next
    INDEX
    Explanations

    specifications, identification, outlining

    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
    ψ
    0.44
    你怎么
    0.43
    杨
    0.42
    myCollision
    0.42
    难
    0.41
    类
    0.41
    误差
    0.41
    下载
    0.40
    复杂的
    0.40
    两
    0.40
    POSITIVE LOGITS
     posit
    0.54
     positiv
    0.54
     positi
    0.50
     buena
    0.48
     secu
    0.47
     innov
    0.47
     indien
    0.47
     expedit
    0.46
     affirmat
    0.46
     الخير
    0.45
    Activations Density 0.030%

    No Known Activations