© 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. 66956
    Prev
    Next
    INDEX
    Explanations

    scientific and programming contexts

    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
    3
    -1.58
     vielmehr
    -1.51
     $
    -1.51
    ’
    -1.48
    (/^
    -1.48
     metálico
    -1.45
     longtime
    -1.42
     anledning
    -1.41
    t
    -1.41
     onsdag
    -1.39
    POSITIVE LOGITS
     inaug
    1.57
     vitrine
    1.52
     impreg
    1.49
     luminos
    1.42
     maniere
    1.38
     séjours
    1.38
    și
    1.37
    楔
    1.37
    ITECH
    1.36
     nerv
    1.35
    Activations Density 0.000%

    No Known Activations