© 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. 130383
    Prev
    Next
    INDEX
    Explanations

    protecting yourself

    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
     from
    -2.64
     for
    -2.48
     by
    -2.41
     like
    -2.19
     in
    -2.17
     through
    -2.09
     are
    -1.73
     with
    -1.62
     via
    -1.45
     then
    -1.37
    POSITIVE LOGITS
    秾
    1.59
     italiens
    1.45
    asts
    1.43
    기도
    1.42
    citement
    1.40
    說
    1.38
     Papel
    1.34
    quelize
    1.32
    1.31
     Corazón
    1.30
    Activations Density 0.050%

    No Known Activations