© 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. 110949
    Prev
    Next
    INDEX
    Explanations

    ----

    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
    that
    -2.64
    I
    -2.63
    龊
    -2.45
    o
    -2.38
     voordeel
    -2.33
     verschil
    -2.31
     robić
    -2.30
     jesteśmy
    -2.28
    ar
    -2.23
     impeccable
    -2.17
    POSITIVE LOGITS
    '
    2.84
    は
    2.52
    ి
    2.48
    ݯ
    2.47
     byen
    2.47
    喾
    2.44
    訁
    2.39
     resembling
    2.31
    い
    2.27
    垍
    2.25
    Activations Density 0.006%

    No Known Activations