© 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. 106603
    Prev
    Next
    INDEX
    Explanations

    US auto, Energy Limits

    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
     or
    -0.93
     should
    -0.85
     Sak
    -0.84
     seeking
    -0.80
     hacer
    -0.79
    asjon
    -0.79
    ⛴
    -0.77
     membuatnya
    -0.77
     for
    -0.75
     dozens
    -0.75
    POSITIVE LOGITS
    ecke
    0.86
    ordre
    0.84
     feu
    0.84
     bact
    0.80
     Volunt
    0.78
     liege
    0.78
    ressen
    0.78
    yaxis
    0.77
    镲
    0.77
    ISTRATION
    0.76
    Activations Density 0.002%

    No Known Activations