© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9828
    Prev
    Next
    INDEX
    Explanations

    offers an

    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
     in
    -2.25
     on
    -2.14
     there
    -2.06
     as
    -1.98
     they
    -1.97
     it
    -1.84
     these
    -1.80
     those
    -1.70
     by
    -1.64
     and
    -1.63
    POSITIVE LOGITS
     levar
    1.68
     garantir
    1.62
     borracha
    1.61
    :"
    1.60
     représent
    1.60
     grátis
    1.59
     thrills
    1.56
    Ã
    1.55
    /"
    1.55
     lui
    1.55
    Activations Density 0.032%

    No Known Activations