© 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. 10-GEMMASCOPE-RES-131K
    7. 66096
    Prev
    Next
    INDEX
    Explanations

    methods

    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
     was
    -2.91
    ’
    -2.50
    </h1>
    -2.50
    穑
    -2.47
    e
    -2.45
    いえば
    -2.28
    ’，
    -2.27
     then
    -2.23
    ྂ
    -2.22
    section
    -2.17
    POSITIVE LOGITS
    </em>
    3.48
    It
    3.02
     höhere
    2.64
    <td>
    2.39
    0
    2.36
    勍
    2.36
    However
    2.34
    st
    2.30
    CHREIB
    2.30
     Atención
    2.22
    Activations Density 0.019%

    No Known Activations