© 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. 80815
    Prev
    Next
    INDEX
    Explanations

    media content

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

    dispute centered heritage

    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
    に向け
    0.54
     ನಡೆಯ
    0.51
    orithm
    0.46
     দৌড়ে
    0.45
    ringen
    0.45
    षक
    0.45
    8
    0.45
    防控
    0.44
     एक्सरसाइज
    0.44
    स्ड
    0.43
    POSITIVE LOGITS
     touristic
    0.46
     رکھنا
    0.44
    🎞
    0.43
     patrimoine
    0.41
    Compart
    0.41
     הרבה
    0.41
    وات
    0.41
     যা
    0.41
     також
    0.41
    收藏
    0.41
    Activations Density 0.002%

    No Known Activations