© 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. 40495
    Prev
    Next
    INDEX
    Explanations

    firsts in context

    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
     surpren
    -1.59
    más
    -1.55
    diğimiz
    -1.47
     paroi
    -1.47
     segítség
    -1.47
     hés
    -1.47
     mismas
    -1.45
     mesmas
    -1.44
     thoſe
    -1.44
     Não
    -1.44
    POSITIVE LOGITS
     of
    2.06
     to
    2.03
     this
    1.88
     in
    1.84
    in
    1.82
    j
    1.81
     on
    1.70
     after
    1.63
     that
    1.59
    on
    1.55
    Activations Density 0.082%

    No Known Activations