© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31911
    Prev
    Next
    INDEX
    Explanations

    calories, sugar, protein

    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_40_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
    묭
    0.49
    卤
    0.43
    ถ่าย
    0.41
    brown
    0.41
    {\'
    0.41
    籿
    0.41
     afro
    0.40
    InputNum
    0.40
    撮影
    0.39
    backgroundSplit
    0.39
    POSITIVE LOGITS
     cranberries
    0.45
     Cran
    0.44
     conten
    0.44
     Crom
    0.42
     LTP
    0.40
     Hertz
    0.40
     NTP
    0.40
    蟬
    0.40
    enton
    0.40
     pleasing
    0.39
    Activations Density 0.000%

    No Known Activations