© 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. 8158
    Prev
    Next
    INDEX
    Explanations

    work tasks and projects

    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
    ’
    -1.77
    箋
    -1.47
     vagyok
    -1.42
    c
    -1.35
     trekken
    -1.32
     verts
    -1.29
     gedachten
    -1.29
     leggen
    -1.27
     arbeta
    -1.27
     خير
    -1.25
    POSITIVE LOGITS
     getan
    1.65
     mūsų
    1.64
     work
    1.59
    ']")
    1.49
     teils
    1.47
     nuova
    1.41
     influential
    1.41
     recently
    1.41
     augmenté
    1.39
    ESTY
    1.39
    Activations Density 0.049%

    No Known Activations