© 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. 89393
    Prev
    Next
    INDEX
    Explanations

    listing, reserved, backyard chickens, distinct understanding

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

    network congestion and concepts

    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
    BOSS
    0.54
    ُر
    0.52
    NEW
    0.50
    pH
    0.50
    vě
    0.49
    Ũ
    0.49
    performance
    0.48
    彗
    0.48
    Ɛ
    0.48
    boss
    0.47
    POSITIVE LOGITS
     온라인
    0.46
     отзы
    0.46
     годов
    0.46
     runes
    0.45
     днем
    0.44
    matik
    0.44
     ungg
    0.44
     literals
    0.43
     ГО
    0.42
     udě
    0.41
    Activations Density 0.000%

    No Known Activations