© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120670
    Prev
    Next
    INDEX
    Explanations

    on behalf of

    np_acts-logits-general · gemini-2.5-flash-lite

    metaphorical descriptions of AI capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     herum
    0.47
     함수의
    0.46
    熵
    0.44
    ALITY
    0.44
    极限
    0.43
    ElementsBy
    0.43
     নিয়ন্ত্রণে
    0.43
    ITHUB
    0.43
     glycemic
    0.42
    Framebuffer
    0.42
    POSITIVE LOGITS
    ใหญ่
    0.44
    ہ
    0.43
     and
    0.43
     Floral
    0.43
    및
    0.41
    ने
    0.41
    विशेष
    0.40
     lull
    0.40
     спокой
    0.40
     edhe
    0.39
    Activations Density 0.000%

    No Known Activations