© 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. 44555
    Prev
    Next
    INDEX
    Explanations

    classification levels and grades

    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
    észetes
    -1.80
    のいい
    -1.61
     贺
    -1.61
    ]-\
    -1.59
     löst
    -1.50
    uttgart
    -1.48
    騭
    -1.46
    采用了
    -1.45
     materiál
    -1.43
    rogates
    -1.43
    POSITIVE LOGITS
    _
    1.91
    '
    1.61
    z
    1.59
    ؛
    1.50
    of
    1.44
    A
    1.41
     craftsmanship
    1.40
     наверное
    1.39
    If
    1.38
     alimenti
    1.38
    Activations Density 0.012%

    No Known Activations