© 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. 123542
    Prev
    Next
    INDEX
    Explanations

    interstellar federation

    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
     will
    0.49
    ми
    0.48
    าน
    0.47
    ي
    0.46
    inois
    0.44
     atta
    0.43
     හොඳ
    0.43
     is
    0.42
    نم
    0.42
    ignal
    0.42
    POSITIVE LOGITS
    Czech
    0.50
    Russian
    0.48
     किंवा
    0.48
    Putin
    0.47
     または
    0.47
     ছিলোনা
    0.44
     Slovak
    0.44
    Kyr
    0.44
    ǹ
    0.44
     Estadística
    0.43
    Activations Density 0.002%

    No Known Activations