© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130285
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     especialidad
    -1.14
    grunns
    -1.10
    熜
    -1.09
    исп
    -1.06
     statistique
    -1.06
    페이지
    -1.05
    ꯅ
    -1.05
     utilisés
    -1.05
    lück
    -1.03
     funcionario
    -1.03
    POSITIVE LOGITS
    v
    1.19
     on
    1.13
     through
    1.09
    z
    1.09
    s
    1.04
     to
    0.98
     -
    0.97
     in
    0.96
    x
    0.96
    ll
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.