© 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. 144020
    Prev
    Next
    INDEX
    Explanations

    gross income, chosen fat

    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
    
    0.51
     بارے
    0.47
     და
    0.47
    ერს
    0.46
    ொருள்
    0.46
     ጉዳ
    0.45
     planification
    0.45
    屆
    0.44
    -$\
    0.44
    區
    0.44
    POSITIVE LOGITS
     undet
    0.46
     microl
    0.45
     sams
    0.45
     outliers
    0.44
     bowlers
    0.44
    BOW
    0.44
     fuller
    0.43
     self
    0.42
    O
    0.42
    睬
    0.42
    Activations Density 0.000%

    No Known Activations