© 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. 183468
    Prev
    Next
    INDEX
    Explanations

    service provider not insured

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

    Minecraft server Minecraft Fabric

    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
     ສຳ
    0.49
     desafíos
    0.48
     решений
    0.47
     tesam
    0.43
     感
    0.43
     actuales
    0.43
    workspaceFolder
    0.43
     diferencias
    0.42
     gön
    0.42
    cel
    0.42
    POSITIVE LOGITS
    isasi
    0.47
     Ajouter
    0.47
     sker
    0.46
     Heller
    0.46
    ل
    0.46
    িন
    0.44
     فقد
    0.43
     plaus
    0.43
    ガ
    0.43
    好吃
    0.43
    Activations Density 0.000%

    No Known Activations