© 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. 20985
    Prev
    Next
    INDEX
    Explanations

    namespaces and imports

    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
    6
    -2.00
    4
    -1.91
    2
    -1.89
    5
    -1.77
     it
    -1.66
    (
    -1.52
    7
    -1.46
    ti
    -1.45
    8
    -1.45
    lon
    -1.42
    POSITIVE LOGITS
    変わらず
    1.80
    诳
    1.77
     стоковая
    1.76
     also
    1.70
     ciertamente
    1.70
     mundos
    1.63
     resistentes
    1.59
     emphatically
    1.59
    cuer
    1.58
     онъ
    1.56
    Activations Density 0.022%

    No Known Activations