© 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. 10-GEMMASCOPE-RES-131K
    7. 73341
    Prev
    Next
    INDEX
    Explanations

    pro- prefix

    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
     exceptional
    -1.86
     exclusivamente
    -1.76
     superb
    -1.69
     effectuer
    -1.57
    in
    -1.57
    컫
    -1.56
    全都
    -1.56
     faisant
    -1.55
    """
    -1.48
     mittler
    -1.48
    POSITIVE LOGITS
     appelez
    1.80
    他們
    1.63
     setelah
    1.63
     для
    1.55
     When
    1.51
     Regardless
    1.50
     يساعد
    1.48
     Whatever
    1.48
     Surprisingly
    1.48
     große
    1.47
    Activations Density 0.079%

    No Known Activations