© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44709
    Prev
    Next
    INDEX
    Explanations

    written by author

    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
    骉
    -1.49
     卒業
    -1.40
    怎麼辦
    -1.38
     มัน
    -1.38
    aarrggbb
    -1.38
     a
    -1.38
    が含ま
    -1.37
     таких
    -1.35
     possibilidade
    -1.34
     preparada
    -1.34
    POSITIVE LOGITS
     by
    2.47
     which
    1.89
     even
    1.84
     for
    1.70
     walaupun
    1.66
     Each
    1.64
     although
    1.61
     tenían
    1.59
    íficos
    1.55
     навіть
    1.55
    Activations Density 0.088%

    No Known Activations