© 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. 110376
    Prev
    Next
    INDEX
    Explanations

    work starts, directors meeting, diverse community

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

    biological and relational concepts

    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
     huv
    0.48
    UN
    0.45
     fwrite
    0.44
    TIM
    0.43
     sunscreen
    0.42
     쭉
    0.42
    yld
    0.42
     enquiry
    0.40
    博客
    0.40
     kekuatan
    0.40
    POSITIVE LOGITS
    /+
    0.44
     μετά
    0.44
     पड़ती
    0.44
     мили
    0.44
     Чер
    0.44
     чер
    0.43
     burb
    0.43
    EnglishMarks
    0.41
     मिलती
    0.41
     情
    0.41
    Activations Density 0.001%

    No Known Activations