© 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. 93093
    Prev
    Next
    INDEX
    Explanations

    format, parse, normalize

    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
     volcanoes
    -0.94
    erialized
    -0.91
    oni
    -0.87
    omi
    -0.84
    封装
    -0.83
    erialization
    -0.83
     网站
    -0.82
    viem
    -0.82
    ânica
    -0.81
    UEFA
    -0.81
    POSITIVE LOGITS
     into
    1.63
     as
    1.33
     for
    1.31
     to
    1.16
     response
    1.08
     time
    1.03
     number
    1.00
     value
    0.95
     received
    0.95
     incoming
    0.94
    Activations Density 0.029%

    No Known Activations