© 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. 10-GEMMASCOPE-RES-131K
    7. 60517
    Prev
    Next
    INDEX
    Explanations

    professional

    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
     Their
    -1.60
     preocupar
    -1.59
    РЫ
    -1.56
    都不是
    -1.55
     harán
    -1.55
     afectan
    -1.55
     encontro
    -1.54
    ?
    -1.53
     quieren
    -1.52
     mencionó
    -1.52
    POSITIVE LOGITS
    U
    1.93
    although
    1.77
    C
    1.77
     ?',
    1.73
    ......”
    1.69
    Although
    1.68
     noter
    1.68
    </u>
    1.66
    ↵
    1.65
     parlement
    1.63
    Activations Density 0.011%

    No Known Activations