© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    code element types

    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
    when
    -1.72
    F
    -1.71
    of
    -1.67
    Now
    -1.65
     their
    -1.62
     which
    -1.59
    彼らは
    -1.59
     any
    -1.58
     two
    -1.56
    They
    -1.56
    POSITIVE LOGITS
     cukru
    2.05
     osoba
    1.86
     okno
    1.85
     znam
    1.80
     obrazy
    1.78
    ův
    1.77
     červ
    1.71
     reklama
    1.70
     listop
    1.69
     ozdob
    1.69
    Activations Density 0.042%

    No Known Activations