© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66043
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming contexts

    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_22/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
    twas
    -1.11
    のでは
    -1.08
     relógio
    -1.07
    chaussures
    -1.06
     diritti
    -1.06
     భూ
    -1.05
     chapéu
    -1.05
    impres
    -1.05
    のではなく
    -1.05
    kapat
    -1.02
    POSITIVE LOGITS
     характеристика
    1.09
    ánto
    1.09
     AUSSI
    1.07
    ästi
    1.06
     then
    1.02
    岀
    1.01
    culin
    1.00
    nible
    1.00
     trabajan
    0.99
    roli
    0.98
    Activations Density 0.199%

    No Known Activations