© 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. 37649
    Prev
    Next
    INDEX
    Explanations

    material, cocoa, exercisable, size

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

    current trends and projections

    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
     médical
    0.57
    医疗
    0.51
     Gastroenter
    0.51
     médicas
    0.49
    ukung
    0.48
     Medical
    0.47
     //.
    0.46
     médicale
    0.46
     médic
    0.46
     medica
    0.45
    POSITIVE LOGITS
    setSize
    0.43
    size
    0.42
    Giá
    0.42
     mAh
    0.41
    Money
    0.40
     TRX
    0.40
    Logo
    0.40
    KG
    0.40
    st
    0.39
    V
    0.39
    Activations Density 0.001%

    No Known Activations