© 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. 10-GEMMASCOPE-RES-131K
    7. 7407
    Prev
    Next
    INDEX
    Explanations

    actions with specific outcomes

    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
    وفق
    -1.48
    Boletín
    -1.32
     femininos
    -1.28
    existent
    -1.27
    塤
    -1.27
     incrí
    -1.26
    springen
    -1.23
     camiset
    -1.23
    Its
    -1.23
    delicious
    -1.21
    POSITIVE LOGITS
     by
    1.55
     can
    1.30
     alertDialog
    1.24
     utilizando
    1.23
     –
    1.22
    <em>
    1.20
     лет
    1.19
     you
    1.19
     bequem
    1.19
     will
    1.17
    Activations Density 0.804%

    No Known Activations