© 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. 22-GEMMASCOPE-RES-131K
    4. 39897
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    "",
    
    -1.33
     pantalon
    -1.18
     ferie
    -1.18
    ","\
    -1.18
    %;
    
    -1.17
     atmosfera
    -1.16
    '");
    -1.14
    ")}
    -1.13
    :+:
    -1.13
     individuel
    -1.12
    POSITIVE LOGITS
    for
    1.30
     the
    1.20
     überprü
    1.10
     (!__
    1.09
     furthermore
    1.06
    凄く
    1.06
     для
    1.06
     verfü
    1.04
     apariencia
    1.03
    /
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.