© 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. 10-GEMMASCOPE-RES-131K
    7. 112242
    Prev
    Next
    INDEX
    Explanations

    available at or from

    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
     kompatibel
    -1.66
    
    -1.62
    說
    -1.55
     tandis
    -1.54
     satt
    -1.52
    が高
    -1.51
     bruto
    -1.50
    鷽
    -1.50
    frequently
    -1.50
     verhind
    -1.50
    POSITIVE LOGITS
     by
    2.73
     with
    1.97
     ONLY
    1.84
     after
    1.64
     on
    1.59
     only
    1.56
     or
    1.55
    谞
    1.50
     Despite
    1.48
     would
    1.46
    Activations Density 0.036%

    No Known Activations