© 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. 41967
    Prev
    Next
    INDEX
    Explanations

    what kind of

    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
    蚡
    -1.80
    ांकि
    -1.76
    逦
    -1.67
    badan
    -1.66
    乄
    -1.65
    踯
    -1.65
     exhilar
    -1.63
     wichtigste
    -1.62
    箧
    -1.60
    萏
    -1.57
    POSITIVE LOGITS
     with
    2.31
     had
    1.98
     four
    1.95
     if
    1.94
     three
    1.93
     got
    1.78
     time
    1.77
     went
    1.73
     areas
    1.73
     seven
    1.73
    Activations Density 0.065%

    No Known Activations