© 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. 29195
    Prev
    Next
    INDEX
    Explanations

    explaining how to do

    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
    }]{
    -1.58
    .}(
    -1.49
    +}\
    -1.48
    endforeach
    -1.47
    ">)</
    -1.45
     secrétaire
    -1.41
    $}
    -1.39
    𖣔
    -1.39
    ,:),
    -1.39
     diriger
    -1.35
    POSITIVE LOGITS
     when
    1.88
     what
    1.79
     for
    1.64
     you
    1.60
     latter
    1.56
     why
    1.50
     necessary
    1.49
     how
    1.48
     is
    1.45
     but
    1.44
    Activations Density 0.174%

    No Known Activations