© 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. 77594
    Prev
    Next
    INDEX
    Explanations

    foreign language or non-english text

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

    Wired, AI, professionals

    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
     밝혔
    0.45
     dedim
    0.44
     mr
    0.43
     damal
    0.43
     nisam
    0.42
     %,
    0.41
    었고
    0.41
     sims
    0.41
     viên
    0.40
     cid
    0.40
    POSITIVE LOGITS
    ونی
    0.46
     receber
    0.45
    Choose
    0.44
    ಸೂ
    0.44
    箇
    0.44
    。《
    0.43
    стів
    0.43
     ಉಪಯೋಗ
    0.43
     अफवाह
    0.41
     είναι
    0.41
    Activations Density 0.001%

    No Known Activations