© 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. 73372
    Prev
    Next
    INDEX
    Explanations

    offer various options

    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
     it
    -1.89
     많은
    -1.66
     many
    -1.55
     more
    -1.54
     well
    -1.48
     zamiast
    -1.45
     It
    -1.40
     and
    -1.39
     had
    -1.38
     since
    -1.37
    POSITIVE LOGITS
    bonsoir
    1.63
    ୌ
    1.50
    ValueGeneration
    1.49
    ij
    1.49
    matician
    1.48
    therosclerosis
    1.45
    vereignty
    1.43
    isierung
    1.42
    ౧
    1.42
     BorderRadius
    1.41
    Activations Density 0.185%

    No Known Activations