© 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. 126420
    Prev
    Next
    INDEX
    Explanations

    rhyme scheme

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

    semicolon or colon followed by capital letter

    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
    ებულია
    0.42
     ماشینونه
    0.40
    pageY
    0.39
    ✰
    0.37
    ]+/
    0.36
    に加え
    0.36
     پروگرام
    0.35
    goTo
    0.35
    ینا
    0.35
    "]/
    0.35
    POSITIVE LOGITS
     вашей
    0.42
     WELL
    0.38
     QUE
    0.38
     от
    0.38
    спо
    0.38
     ее
    0.38
    </h2>
    0.38
    utar
    0.38
     возь
    0.38
    orie
    0.37
    Activations Density 0.001%

    No Known Activations