© 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. 78919
    Prev
    Next
    INDEX
    Explanations

    coordinates and dimensions

    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
     considered
    -0.80
     helped
    -0.79
     у
    -0.76
    喬
    -0.75
     walked
    -0.75
     uncon
    -0.75
    包含
    -0.75
     đa
    -0.75
     create
    -0.74
     mostly
    -0.74
    POSITIVE LOGITS
    uzi
    0.90
     场
    0.87
     naturel
    0.84
     biblia
    0.83
     Biblia
    0.83
     Jupyter
    0.79
    jeros
    0.79
    ﺳ
    0.77
    stdio
    0.77
    ():
    0.76
    Activations Density 0.025%

    No Known Activations