© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130692
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    他们的
    -1.48
    IANGLES
    -1.45
    unakan
    -1.45
    他們
    -1.38
    Fourni
    -1.38
    তথ্য
    -1.36
    きている
    -1.36
     escuchado
    -1.35
     grayish
    -1.34
    mäßigen
    -1.34
    POSITIVE LOGITS
    of
    2.14
    !
    1.92
    un
    1.81
    na
    1.78
    ar
    1.77
     the
    1.75
    T
    1.71
    lu
    1.64
    #
    1.63
    B
    1.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.