© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108498
    Prev
    Next
    INDEX
    Explanations

    seem to be

    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
     seraient
    -0.96
     and
    -0.95
     jendela
    -0.91
     nagyon
    -0.90
    usstsein
    -0.89
    estens
    -0.89
     opravdu
    -0.89
     póster
    -0.86
     PUEDE
    -0.86
     כאשר
    -0.85
    POSITIVE LOGITS
     to
    1.36
     an
    0.94
     a
    0.91
     designed
    0.91
     destined
    0.89
    可惜
    0.89
     preferable
    0.89
     altogether
    0.88
     especially
    0.87
     at
    0.87
    Activations Density 0.029%

    No Known Activations