© 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. 34-GEMMASCOPE-RES-131K
    7. 63343
    Prev
    Next
    INDEX
    Explanations

    Mozilla Public License

    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_34/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
     могут
    -2.03
     может
    -1.88
     sẽ
    -1.77
    probably
    -1.73
     may
    -1.73
     olabilir
    -1.63
     pueden
    -1.62
     võib
    -1.59
     może
    -1.59
     peuvent
    -1.58
    POSITIVE LOGITS
     is
    2.80
     isn
    2.11
     has
    1.93
     fails
    1.87
     wasn
    1.86
     weren
    1.84
     ever
    1.78
     didn
    1.78
     hasn
    1.76
     were
    1.73
    Activations Density 0.170%

    No Known Activations