© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65897
    Prev
    Next
    INDEX
    Explanations

    up to indicating maximums

    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
     nying
    -2.30
    G
    -2.13
    the
    -2.03
    ０
    -2.03
    in
    -2.02
     kuan
    -1.98
    B
    -1.95
     andere
    -1.82
    去
    -1.79
    our
    -1.76
    POSITIVE LOGITS
     jeweiligen
    2.23
     entsprechenden
    1.86
     infancia
    1.86
     schnellen
    1.83
    rolex
    1.75
     anún
    1.73
     Ganzen
    1.72
    巂
    1.68
     sebelum
    1.68
    发言
    1.67
    Activations Density 0.012%

    No Known Activations