© 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. 24035
    Prev
    Next
    INDEX
    Explanations

    jQuery document ready

    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
     we
    -1.39
     then
    -1.37
     erhält
    -1.34
     use
    -1.32
     were
    -1.25
    <th>
    -1.22
    ทำให้
    -1.16
    alamus
    -1.12
     można
    -1.12
    ']]
    -1.11
    POSITIVE LOGITS
    klaim
    1.26
    回目の
    1.23
     theses
    1.21
    /
    1.17
    回目
    1.17
    姈
    1.13
     competitivos
    1.13
     artikkelen
    1.13
     queijo
    1.12
    Према
    1.12
    Activations Density 0.043%

    No Known Activations