© 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. 26881
    Prev
    Next
    INDEX
    Explanations

    HTML tags and numerical sequences

    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
    どんど
    0.55
     Kontext
    0.48
    وها
    0.47
    klik
    0.45
    льна
    0.44
    𒀸
    0.43
    ковые
    0.43
    প্রথম
    0.43
    '=>$
    0.43
    ণিজ্য
    0.43
    POSITIVE LOGITS
     confid
    0.47
     sentimiento
    0.46
     '<
    0.45
    </code>
    0.43
    ");
    0.42
     '
    0.41
    rupulous
    0.40
     './
    0.40
     Jacksonville
    0.40
     widespread
    0.39
    Activations Density 0.003%

    No Known Activations