© 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. 197304
    Prev
    Next
    INDEX
    Explanations

    apple tv, latest products, call early

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

    clean system

    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
    т
    0.50
     inco
    0.47
     corrispond
    0.47
    ้ว
    0.46
     ura
    0.46
    య
    0.46
     incoherent
    0.46
    าท
    0.46
    সম্প
    0.45
     economico
    0.45
    POSITIVE LOGITS
    🏆
    0.50
    intis
    0.48
    NHL
    0.46
    aien
    0.46
    并购
    0.45
    ai
    0.45
    aji
    0.45
    户外
    0.44
    :
    0.44
     tekl
    0.42
    Activations Density 0.000%

    No Known Activations