© 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. 107852
    Prev
    Next
    INDEX
    Explanations

    IEEE standards

    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
    vistar
    -0.78
     bachelor
    -0.76
     juillet
    -0.75
    捏
    -0.74
    JACK
    -0.74
    ganta
    -0.74
     quinto
    -0.73
     eje
    -0.71
    八卦
    -0.71
    oldown
    -0.71
    POSITIVE LOGITS
     IEEE
    1.24
    IEEE
    1.13
     Std
    0.88
     ieee
    0.83
    Çok
    0.77
    Akan
    0.77
    Postup
    0.76
     Broadband
    0.75
     standards
    0.74
    GORITHM
    0.73
    Activations Density 0.034%

    No Known Activations