© 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. 130154
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    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
     all
    -1.56
    return
    -1.37
     других
    -1.35
     \&
    -1.34
     always
    -1.30
     )
    -1.28
    нный
    -1.28
     of
    -1.27
    其它
    -1.23
    7
    -1.23
    POSITIVE LOGITS
    oughby
    1.41
    ⃤
    1.40
    pantalón
    1.40
    alion
    1.38
     kabát
    1.38
    pantalon
    1.33
    cún
    1.31
     sikkert
    1.31
     mezclar
    1.30
    鈮
    1.30
    Activations Density 0.009%

    No Known Activations