© 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. 241732
    Prev
    Next
    INDEX
    Explanations

    multi-word expressions, foreign words

    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
     hielo
    0.45
    烺
    0.44
     frio
    0.43
     frío
    0.41
     anyag
    0.41
    说法
    0.41
    Aware
    0.40
    влено
    0.40
    狲
    0.40
    什么是
    0.40
    POSITIVE LOGITS
     joseph
    0.48
     amplitude
    0.47
     विश्वसनीय
    0.47
     開始
    0.46
     converge
    0.45
    كثر
    0.45
     ಕೆಲಸ
    0.44
     repet
    0.44
     القسمه
    0.43
     institutional
    0.43
    Activations Density 0.000%

    No Known Activations