© 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. 34-GEMMASCOPE-RES-131K
    7. 77264
    Prev
    Next
    INDEX
    Explanations

    dimensions represented as number x number

    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_34/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
     наконец
    -0.96
    ProductList
    -0.76
    íte
    -0.75
    ̎
    -0.73
    પ
    -0.73
     Yen
    -0.73
    ahn
    -0.73
     JF
    -0.71
    upan
    -0.71
    żd
    -0.71
    POSITIVE LOGITS
     square
    0.84
     SQUARE
    0.78
    squared
    0.77
    getJSONArray
    0.75
    sqr
    0.74
    YX
    0.73
     Pursuant
    0.73
     GRID
    0.72
     القر
    0.72
     squared
    0.72
    Activations Density 0.045%

    No Known Activations