© 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. 39543
    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
     like
    -1.77
     such
    -1.73
     so
    -1.37
     silnika
    -1.22
    とおり
    -1.16
    cucina
    -1.09
     такі
    -1.09
     aguacate
    -1.05
     going
    -1.05
     from
    -1.05
    POSITIVE LOGITS
    —¿
    1.41
     Identität
    1.29
    ৩
    1.23
    '][$
    1.23
    ⟩
    1.22
     Vikipedi
    1.21
    exitRule
    1.20
    Generator
    1.20
    ВА
    1.16
                               
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.