© 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. 158506
    Prev
    Next
    INDEX
    Explanations

    locations and academic details

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

    decoding, values, Evolution, disrupts, region, secure, You, submitted

    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
     Neces
    0.56
     Produtos
    0.55
     Productos
    0.55
     propiedad
    0.55
     Products
    0.54
     conhe
    0.53
     Producto
    0.52
    པ
    0.51
     productos
    0.49
    ortic
    0.49
    POSITIVE LOGITS
    ukan
    0.46
    ytically
    0.46
    ToJson
    0.45
    aklar
    0.45
    StateToProps
    0.44
    AvlTree
    0.43
    ลาคม
    0.43
    itamento
    0.43
    ्यक्रम
    0.42
    igneur
    0.41
    Activations Density 0.000%

    No Known Activations