© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7400
    Prev
    Next
    INDEX
    Explanations

    action, consequence, or relation

    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
     liknande
    -1.70
    糴
    -1.60
     différents
    -1.52
    atste
    -1.51
    ⎔
    -1.48
     kağıdı
    -1.46
     PUSTAKA
    -1.46
     réservés
    -1.45
     extrêmement
    -1.44
     pantalones
    -1.42
    POSITIVE LOGITS
     because
    2.52
     in
    2.33
     through
    2.31
     despite
    2.11
     before
    2.06
     the
    2.00
     from
    1.99
     if
    1.93
     within
    1.92
     a
    1.81
    Activations Density 0.183%

    No Known Activations