© 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. 178901
    Prev
    Next
    INDEX
    Explanations

    upcoming Olympic Games

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

    values and principles

    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
     since
    0.48
     znacznie
    0.48
     MODELS
    0.46
    ִי
    0.45
    ス
    0.44
    ÇA
    0.44
     varie
    0.44
    す
    0.43
    펀
    0.42
    ָד
    0.42
    POSITIVE LOGITS
    indentLevel
    0.52
    TextureAsset
    0.49
    рные
    0.47
    獭
    0.46
    "])
    0.46
    LabelTool
    0.45
    sick
    0.44
    hés
    0.44
     ribosomal
    0.44
     अन्न
    0.44
    Activations Density 0.001%

    No Known Activations