© 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. 19095
    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
    tisserie
    -0.92
    ☇
    -0.90
    _
    -0.90
    ೇ
    -0.90
     fiume
    -0.89
    жает
    -0.85
     realizarse
    -0.84
    geqslant
    -0.82
     tfsi
    -0.82
     shallots
    -0.82
    POSITIVE LOGITS
    VIRON
    0.98
     viewHolder
    0.97
    Horário
    0.94
     preuß
    0.94
     Geschäft
    0.94
     "@/
    0.92
    ⓿
    0.91
     tvar
    0.90
    Preamble
    0.90
     But
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.