© 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. 13055
    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
     —
    -1.18
    —
    -1.17
    ,「
    -1.10
     to
    -1.03
    geries
    -1.02
     considération
    -0.94
     «
    -0.94
    Less
    -0.91
    ból
    -0.90
    neighbour
    -0.90
    POSITIVE LOGITS
     depoz
    1.22
     streamlining
    1.14
     emite
    1.13
    Hvorfor
    1.11
     opinião
    1.11
     décider
    1.11
     atividade
    1.10
    ጦ
    1.10
    Hvad
    1.09
    asy
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.