© 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. 99948
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    vertebrates
    -1.45
    殽
    -1.35
     in
    -1.34
     regulate
    -1.31
     one
    -1.30
     nélkül
    -1.27
     who
    -1.23
    sistence
    -1.23
     utilise
    -1.23
     nélk
    -1.22
    POSITIVE LOGITS
    r
    1.68
    鎳
    1.60
    ción
    1.48
    .''
    1.47
    t
    1.44
     våra
    1.41
     addirittura
    1.35
     изпол
    1.30
    どい
    1.28
    .”
    1.27
    Activations Density 0.051%

    No Known Activations