© 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. 48697
    Prev
    Next
    INDEX
    Explanations

    React JavaScript code

    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
     ত
    0.40
    ScienceStudent
    0.39
     addict
    0.39
    theria
    0.39
     m
    0.38
     addictive
    0.37
     fraction
    0.35
    Entering
    0.35
    bitkan
    0.35
     progr
    0.34
    POSITIVE LOGITS
    తా
    0.43
    ๋
    0.43
    tay
    0.39
    mény
    0.38
     আমেরিকান
    0.38
     американ
    0.38
     Hays
    0.37
     especializado
    0.37
    лле
    0.37
     keuze
    0.37
    Activations Density 0.003%

    No Known Activations