© 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. 116109
    Prev
    Next
    INDEX
    Explanations

    multilingual descriptions

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

    explanations and code formatting

    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
    ről
    0.52
    RUNTIME
    0.46
    ytte
    0.46
    嵘
    0.45
    éa
    0.45
    eners
    0.42
    ATEG
    0.42
    yczy
    0.42
    اقی
    0.42
    orage
    0.41
    POSITIVE LOGITS
    是用
    0.55
     ANY
    0.53
     التص
    0.49
     Escola
    0.45
    瓣
    0.45
    ._
    0.44
     правила
    0.44
     た
    0.43
     любой
    0.43
     Estas
    0.43
    Activations Density 0.001%

    No Known Activations