© 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. 8243
    Prev
    Next
    INDEX
    Explanations

    intent to action

    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
    {
    -1.45
    ﹶ
    -1.35
     zapato
    -1.33
     실패
    -1.32
     before
    -1.31
     barva
    -1.31
    ﮨ
    -1.30
     camisetas
    -1.30
     illustrationer
    -1.29
     πριν
    -1.27
    POSITIVE LOGITS
     gleichen
    1.37
     tournage
    1.34
     solamente
    1.31
     it
    1.31
     \
    1.30
     bénévol
    1.30
    Anyways
    1.27
     หลัง
    1.26
     continúas
    1.23
    ‘
    1.22
    Activations Density 0.037%

    No Known Activations