© 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. 162208
    Prev
    Next
    INDEX
    Explanations

    sizes and measurements

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

    no single rule

    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
     proizvoda
    0.47
    ͕
    0.46
     antal
    0.45
     toko
    0.43
     derivados
    0.43
     monograph
    0.43
     sonuc
    0.42
     alatt
    0.42
     phospholipid
    0.42
     sayıda
    0.42
    POSITIVE LOGITS
     ور
    0.46
    areas
    0.46
    胃
    0.46
    y
    0.45
    revolutionary
    0.45
     बखूबी
    0.45
    n
    0.44
    re
    0.43
    اب
    0.43
    ابط
    0.43
    Activations Density 0.000%

    No Known Activations