© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68303
    Prev
    Next
    INDEX
    Explanations

    dates and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -1.43
     braccia
    -1.38
     apunta
    -1.31
    2
    -1.29
     felicitación
    -1.27
     hierv
    -1.27
    7
    -1.27
     estará
    -1.25
    6
    -1.24
     risorse
    -1.23
    POSITIVE LOGITS
    二年
    1.55
     Gegenteil
    1.30
     οποίο
    1.30
     Պ
    1.29
    ɫ
    1.27
    水墨
    1.25
    庖
    1.23
     subjecting
    1.22
     мы
    1.21
    üğü
    1.21
    Activations Density 0.000%

    No Known Activations