© 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. 122436
    Prev
    Next
    INDEX
    Explanations

    prepositions completing phrases

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

    primary peristalsis, track consistently, curly braces

    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
    ্ক
    0.49
    ровано
    0.45
    σμ
    0.45
    率は
    0.44
    状
    0.44
    umet
    0.44
    starch
    0.43
    <0x80>
    0.43
    ญี่ปุ่น
    0.43
     cục
    0.42
    POSITIVE LOGITS
     appliqu
    0.58
     applic
    0.52
     I
    0.49
     gaf
    0.48
     imit
    0.47
    ið
    0.47
    appliqu
    0.47
     iman
    0.46
     verilen
    0.46
     möglichen
    0.45
    Activations Density 0.001%

    No Known Activations