© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105201
    Prev
    Next
    INDEX
    Explanations

    Diffuse idiopathic, Forsyth

    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
     of
    -1.63
    providedIn
    -1.61
     a
    -1.58
     \
    -1.42
    '
    -1.41
    (
    -1.39
     '',
    -1.36
    _
    -1.35
     our
    -1.34
     通販
    -1.34
    POSITIVE LOGITS
     iedereen
    1.69
    Stap
    1.64
     they
    1.64
     anunciado
    1.57
     it
    1.48
    vitational
    1.46
     vooral
    1.45
    adesivo
    1.45
     bepaalde
    1.44
     dostup
    1.43
    Activations Density 0.009%

    No Known Activations