© 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. 223575
    Prev
    Next
    INDEX
    Explanations

    English, car, champions, concept, train, aristocracy

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

    foreign characters

    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
     Ար
    0.52
    <unused31>
    0.47
    because
    0.45
    nutrient
    0.45
     فريق
    0.44
     لأنه
    0.44
     nho
    0.43
     omdat
    0.43
    frameCount
    0.43
     Top
    0.43
    POSITIVE LOGITS
    ना
    0.49
    ラップ
    0.45
    <0xB4>
    0.44
    支
    0.40
    хол
    0.39
    Კ
    0.39
    溸
    0.38
    ンジ
    0.38
     घंटा
    0.38
    佈
    0.38
    Activations Density 0.000%

    No Known Activations