© 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. 74801
    Prev
    Next
    INDEX
    Explanations

    im

    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
    ↵↵
    -3.06
     From
    -2.75
     of
    -2.55
     In
    -2.41
     After
    -2.39
     With
    -2.28
     werden
    -2.23
     pleas
    -2.20
     Various
    -2.20
     perlahan
    -2.17
    POSITIVE LOGITS
    
    3.70
    廰
    3.08
    慙
    3.06
    á
    2.97
    im
    2.84
    ⢌
    2.84
    l
    2.75
    y
    2.69
    猻
    2.69
    n
    2.58
    Activations Density 0.018%

    No Known Activations