© 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. 145816
    Prev
    Next
    INDEX
    Explanations

    numbers or lists

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

    spending free

    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
     of
    0.48
    ște
    0.46
    spe
    0.46
    ेटर
    0.45
    వారి
    0.45
     fint
    0.44
    困
    0.44
    listOf
    0.44
    useppe
    0.43
    াড়
    0.43
    POSITIVE LOGITS
     ഔ
    0.48
    imely
    0.46
     ሳይ
    0.44
     สร้าง
    0.44
    も
    0.44
     عملی
    0.44
     ویکی‌پ
    0.44
    ഔ
    0.43
    大幅
    0.43
    PreferredItem
    0.43
    Activations Density 0.000%

    No Known Activations