© 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. 122387
    Prev
    Next
    INDEX
    Explanations

    dates, book, Inc, Host, urban

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

    moral consistency

    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
    过于
    0.48
    l
    0.48
    greeting
    0.47
    supported
    0.47
    demo
    0.46
    ありました
    0.46
    supports
    0.45
    有助于
    0.45
    raise
    0.43
     сила
    0.43
    POSITIVE LOGITS
     Markt
    0.54
    መር
    0.50
    }\|_{
    0.50
     Yatha
    0.50
     ശ്രദ്ധ
    0.48
    ו
    0.48
    ючи
    0.48
     auk
    0.47
    WordArray
    0.47
    Abi
    0.47
    Activations Density 0.000%

    No Known Activations