© 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. 100624
    Prev
    Next
    INDEX
    Explanations

    digit format specifiers

    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
    either
    -1.92
    ⎔
    -1.72
     mogli
    -1.71
     ici
    -1.48
    țin
    -1.45
     echte
    -1.43
    almost
    -1.41
     either
    -1.40
     [.
    -1.38
    odora
    -1.38
    POSITIVE LOGITS
     increase
    1.82
     bedeut
    1.59
     modernen
    1.58
     praktischen
    1.52
     because
    1.51
     desirable
    1.49
     auß
    1.48
     numbers
    1.46
     with
    1.45
     help
    1.42
    Activations Density 0.001%

    No Known Activations