© 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. 34-GEMMASCOPE-RES-131K
    7. 107647
    Prev
    Next
    INDEX
    Explanations

    special characters and code separators

    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
    textnormal
    -0.80
     empresarial
    -0.74
     mendorong
    -0.74
    IANT
    -0.73
     PDG
    -0.72
     typeface
    -0.69
     Nutrients
    -0.68
    늦
    -0.68
    Shy
    -0.67
    STAT
    -0.66
    POSITIVE LOGITS
     Bundesrepublik
    0.77
     domesti
    0.73
    द
    0.72
    Validation
    0.69
    home
    0.65
     téléphonique
    0.64
     Reynolds
    0.63
    atoire
    0.63
    ول
    0.63
    вало
    0.62
    Activations Density 0.053%

    No Known Activations