© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36889
    Prev
    Next
    INDEX
    Explanations

    starts phrases

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

    JSON schema declarations

    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
     Luca
    0.45
     Heinrich
    0.43
     COLLECT
    0.42
     Shopify
    0.42
    几次
    0.40
     ট্র্যাক
    0.40
    镖
    0.40
    没什么
    0.40
    פתח
    0.39
    像
    0.39
    POSITIVE LOGITS
    তাহার
    0.48
    titor
    0.46
    CAM
    0.45
    lja
    0.45
    क्षर
    0.45
     οποία
    0.44
    alur
    0.43
    এশিয়া
    0.42
    枭
    0.42
     definiert
    0.42
    Activations Density 0.000%

    No Known Activations