© 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. 95775
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific contexts

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

    defining meaning or oneself

    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
     pupils
    0.46
    ЛИ
    0.44
    יר
    0.41
    厠
    0.41
     थ
    0.39
    იზ
    0.39
    дан
    0.39
     conduce
    0.39
    тел
    0.39
    潁
    0.39
    POSITIVE LOGITS
     tedy
    0.47
     vaikka
    0.47
     específicamente
    0.46
     teda
    0.46
    ますが
    0.46
     specifically
    0.44
    বেলা
    0.41
    kirche
    0.41
     সংখ্যাগ
    0.41
    های
    0.40
    Activations Density 0.000%

    No Known Activations