© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108453
    Prev
    Next
    INDEX
    Explanations

    html input tags and attributes

    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_34/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
     wyróż
    -0.82
    marshall
    -0.82
     uitvo
    -0.81
    перь
    -0.81
    HasAnnotation
    -0.80
    =$?
    -0.78
    ås
    -0.78
    蒻
    -0.77
    '>{
    -0.76
    レード
    -0.76
    POSITIVE LOGITS
     placeholder
    1.49
     on
    1.40
     required
    1.25
    placeholder
    1.16
     pattern
    1.08
     disabled
    1.02
     style
    1.02
     parsley
    0.99
     Placeholder
    0.96
     id
    0.93
    Activations Density 0.013%

    No Known Activations