© 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. 220724
    Prev
    Next
    INDEX
    Explanations

    loveseat, Read, Roofing, clubs

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

    technical assets and probabilities

    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
    ك
    0.56
    𝒞
    0.49
    𝓖
    0.48
    ம்
    0.45
    హం
    0.45
    حسن
    0.44
    ियो
    0.43
     humedad
    0.43
    َق
    0.43
    ionali
    0.42
    POSITIVE LOGITS
    walker
    0.49
     เข้า
    0.47
    walk
    0.47
    web
    0.46
     動画
    0.45
     の
    0.45
     이미지
    0.45
     จด
    0.45
    bumps
    0.45
    rous
    0.44
    Activations Density 0.000%

    No Known Activations