© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41559
    Prev
    Next
    INDEX
    Explanations

    fries

    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_16_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
    ]
    0.82
    ي
    0.70
    ing
    0.68
    ні
    0.67
    ণিক
    0.63
     in
    0.63
    วน
    0.63
    watermelon
    0.62
    ಿರುವ
    0.61
    2
    0.61
    POSITIVE LOGITS
     Fries
    0.73
    助于
    0.71
     as
    0.69
     fries
    0.63
     εξ
    0.58
    悧
    0.57
    ἱ
    0.56
     cuffs
    0.55
     ބ
    0.55
     الص
    0.54
    Activations Density 0.001%

    No Known Activations