© 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. 181779
    Prev
    Next
    INDEX
    Explanations

    scientific and foreign language terms

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

    eyes, color, forging, detail, childhood

    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
    দীর্ঘ
    0.46
    న
    0.46
    にある
    0.45
    یہ
    0.45
     publication
    0.44
    针对
    0.44
     OD
    0.43
    این
    0.43
    挂
    0.43
    る
    0.42
    POSITIVE LOGITS
     whiche
    0.48
     राष्ट
    0.45
     polypeptides
    0.44
     क्वांट
    0.44
    vgl
    0.44
     물리
    0.44
     plasmas
    0.43
     hypersonic
    0.43
     alcohols
    0.42
    estrian
    0.42
    Activations Density 0.001%

    No Known Activations