© 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. 10-GEMMASCOPE-RES-131K
    7. 130316
    Prev
    Next
    INDEX
    Explanations

    human behavior and experience

    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
     münchen
    -1.70
     was
    -1.55
    ﮦ
    -1.54
     sebuah
    -1.49
    Two
    -1.46
     citoy
    -1.45
    ="
    -1.43
     héro
    -1.41
     sosok
    -1.37
     ansatte
    -1.37
    POSITIVE LOGITS
     Humanos
    1.56
     derzeit
    1.56
     gebildet
    1.43
     fickle
    1.43
    those
    1.39
     coordinating
    1.38
    ndham
    1.34
     varying
    1.31
     incluindo
    1.31
    human
    1.30
    Activations Density 0.106%

    No Known Activations