© 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. 34-GEMMASCOPE-RES-131K
    7. 98505
    Prev
    Next
    INDEX
    Explanations

    code generated, viewport, opinions

    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
     sillä
    -0.93
     Enquanto
    -0.86
    gemeente
    -0.83
    wicks
    -0.79
    ésie
    -0.79
    SetTitle
    -0.79
     professor
    -0.78
     Grecia
    -0.77
     Mientras
    -0.77
     organizations
    -0.76
    POSITIVE LOGITS
    Generated
    1.02
    ">//
    0.93
     recon
    0.87
    generated
    0.82
    ऐ
    0.79
     generated
    0.78
     соответственно
    0.77
    uparrow
    0.75
     initComponents
    0.75
     design
    0.74
    Activations Density 0.000%

    No Known Activations