© 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. 112035
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    1
    -2.23
    what
    -1.73
    a
    -1.73
    o
    -1.63
     =
    -1.63
    I
    -1.60
    三個
    -1.59
    on
    -1.58
    p
    -1.56
    So
    -1.54
    POSITIVE LOGITS
    옻
    1.58
    hermoso
    1.53
     उनके
    1.45
     tercera
    1.45
    feliz
    1.42
    ВП
    1.41
    俟
    1.41
    gehende
    1.40
     angebra
    1.40
    ziasztok
    1.40
    Activations Density 0.020%

    No Known Activations