© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40955
    Prev
    Next
    INDEX
    Explanations

    soul, team, installed, Dust, commissioned

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <td>
    -1.41
    However
    -1.40
    Although
    -1.36
     that
    -1.25
    Though
    -1.24
    Однако
    -1.24
    
    -1.23
    although
    -1.20
    ка
    -1.19
     from
    -1.16
    POSITIVE LOGITS
    ENBERG
    1.51
    Uganda
    1.48
     mensen
    1.41
     besoin
    1.34
     ещё
    1.32
      
    1.30
    wandel
    1.27
     mooi
    1.25
     ayrı
    1.24
    wendige
    1.23
    Activations Density 0.105%

    No Known Activations