© 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. 41308
    Prev
    Next
    INDEX
    Explanations

    protocol

    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
     Its
    -1.90
     the
    -1.81
     adaptarse
    -1.72
     They
    -1.70
    eadilan
    -1.66
    ONEY
    -1.56
    fır
    -1.53
     if
    -1.51
     quieren
    -1.51
     ('
    -1.48
    POSITIVE LOGITS
     is
    2.03
    G
    1.75
    _
    1.74
     كان
    1.66
     chargée
    1.66
    R
    1.60
     kertas
    1.60
    You
    1.59
     toh
    1.55
    .
    1.52
    Activations Density 0.001%

    No Known Activations