© 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. 95083
    Prev
    Next
    INDEX
    Explanations

    savory meals

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

    eigene, sometimes, blurry, version

    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
     जल्दी
    0.50
     ধীরে
    0.50
     뜨
    0.48
     ರಲ್ಲಿ
    0.47
     '*',
    0.45
    ٣
    0.45
     korist
    0.44
     separar
    0.44
     telefonu
    0.44
    lbrakk
    0.44
    POSITIVE LOGITS
    m
    0.53
    保证
    0.46
    ער
    0.43
    ente
    0.42
    l
    0.42
    mere
    0.41
    நாம்
    0.41
     осуществления
    0.40
    纯
    0.40
     заседа
    0.40
    Activations Density 0.001%

    No Known Activations