© 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. 159161
    Prev
    Next
    INDEX
    Explanations

    districts in, despite an, and otherwise

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

    special characters and structured text

    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
    "
    0.50
     класса
    0.45
     يش
    0.44
     كلم
    0.42
     timestamp
    0.42
    ع
    0.42
     مشترك
    0.42
    opens
    0.41
     haszn
    0.41
     greed
    0.41
    POSITIVE LOGITS
    Доброго
    0.48
     मनाने
    0.45
    嚩
    0.44
     любы
    0.44
    फ़ी
    0.44
    ढ़ा
    0.43
    MutableArray
    0.42
    orne
    0.42
     welder
    0.42
    ETE
    0.42
    Activations Density 0.002%

    No Known Activations