© 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. 61212
    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
    kranz
    -1.09
    Ꭽ
    -0.99
     materie
    -0.95
     haría
    -0.94
    蒾
    -0.92
     konserv
    -0.90
     starting
    -0.90
    って
    -0.90
    姤
    -0.90
    TemporalType
    -0.89
    POSITIVE LOGITS
    šené
    0.97
    станови
    0.96
    roffenen
    0.94
    𝘉
    0.93
    Coch
    0.91
    udra
    0.91
     infuriating
    0.85
     unspeak
    0.84
     shuddered
    0.83
     生産
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.