© 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. 56431
    Prev
    Next
    INDEX
    Explanations

    code and AI

    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
     приходи
    0.48
     canceled
    0.47
     giocare
    0.46
    躊
    0.45
     mortgages
    0.44
     jugar
    0.43
     lacks
    0.43
     diminution
    0.43
    𒌉
    0.42
     pendientes
    0.42
    POSITIVE LOGITS
    v
    0.40
    ifter
    0.39
    棒
    0.39
    に入る
    0.38
    te
    0.38
    ，“
    0.37
    teg
    0.37
    Repe
    0.37
    activate
    0.37
    制
    0.37
    Activations Density 0.001%

    No Known Activations