© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44867
    Prev
    Next
    INDEX
    Explanations

    references to education

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

    scientific sounding

    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
    unn
    0.46
    classical
    0.46
    urethane
    0.46
    randomNumber
    0.46
     흥
    0.45
    btn
    0.45
    thing
    0.45
     シル
    0.45
     partially
    0.44
     सपनों
    0.44
    POSITIVE LOGITS
     Birth
    0.48
    هي
    0.47
    <h6>
    0.46
    <h3>
    0.45
    <h2>
    0.45
     WF
    0.45
     Subject
    0.44
     próxima
    0.44
     Reactors
    0.44
    س
    0.44
    Activations Density 0.000%

    No Known Activations