© 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. 109237
    Prev
    Next
    INDEX
    Explanations

    swing states and districts

    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
     in
    1.18
    </h3>
    0.92
     by
    0.92
    ).
    0.86
    ?
    0.84
    ก
    0.79
    س
    0.79
    在
    0.79
    '
    0.78
    سون
    0.75
    POSITIVE LOGITS
    
    0.81
    ра
    0.80
    رځ
    0.78
    ಳು
    0.77
     ګرځنده
    0.77
     وړاندوینې
    0.74
    ад
    0.74
    突き
    0.73
     حتی
    0.72
    getCharAt
    0.72
    Activations Density 0.001%

    No Known Activations