© 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. 102552
    Prev
    Next
    INDEX
    Explanations

    general terms and concepts

    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
    YCH
    -1.80
     tiga
    -1.74
     ſever
    -1.73
    ZIL
    -1.58
     Añade
    -1.57
    Así
    -1.54
     nimi
    -1.52
     Ý
    -1.52
     dessa
    -1.50
    RIT
    -1.50
    POSITIVE LOGITS
    7
    2.55
    3
    2.47
    1
    2.39
    6
    2.38
    8
    2.36
    5
    2.33
    0
    2.16
    4
    2.05
    9
    1.95
    c
    1.81
    Activations Density 0.040%

    No Known Activations