© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85168
    Prev
    Next
    INDEX
    Explanations

    furniture and sumps

    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
    n
    -3.00
    the
    -2.47
    s
    -2.31
    j
    -2.16
    os
    -1.98
    I
    -1.92
    <em>
    -1.81
     camiset
    -1.80
    </b>
    -1.79
     Kristus
    -1.78
    POSITIVE LOGITS
     dresser
    1.94
    '
    1.89
     "
    1.77
    These
    1.73
     veía
    1.72
    criture
    1.67
    倨
    1.66
    そも
    1.63
     Opiniones
    1.63
    诹
    1.63
    Activations Density 0.005%

    No Known Activations