© 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. 20965
    Prev
    Next
    INDEX
    Explanations

    food balls and snack bites

    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
     dataset
    0.44
    臧
    0.41
     Dataset
    0.41
     PASSWORD
    0.40
    هلاك
    0.40
    酽
    0.40
     storylines
    0.39
    愭
    0.39
    ഗം
    0.38
     datasets
    0.37
    POSITIVE LOGITS
     muffins
    0.99
     cupcakes
    0.98
     mini
    0.88
     donuts
    0.87
     dumplings
    0.87
     bites
    0.84
     snacks
    0.83
     meatballs
    0.82
     bite
    0.81
     snack
    0.80
    Activations Density 0.039%

    No Known Activations