© 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. 99592
    Prev
    Next
    INDEX
    Explanations

    having choices or options

    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
     savent
    -1.55
     ativo
    -1.46
    艄
    -1.42
     seraient
    -1.41
    ܧ
    -1.38
     veulent
    -1.37
     rayures
    -1.34
    圌
    -1.34
     vrais
    -1.34
     quelquefois
    -1.32
    POSITIVE LOGITS
     to
    2.19
     if
    2.06
     with
    1.91
     when
    1.60
     here
    1.58
     in
    1.43
    is
    1.32
     at
    1.30
     after
    1.30
     continue
    1.27
    Activations Density 0.056%

    No Known Activations