© 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. 26618
    Prev
    Next
    INDEX
    Explanations

    determiner noun phrases

    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
     favoris
    -1.59
    AddHtmlAttribute
    -1.44
    begins
    -1.41
     потім
    -1.32
    licopter
    -1.28
    helped
    -1.28
     prière
    -1.27
     случае
    -1.27
    decided
    -1.27
     trhu
    -1.26
    POSITIVE LOGITS
     also
    1.35
    r
    1.26
    h
    1.19
    時間も
    1.15
     is
    1.15
    p
    1.13
     y
    1.12
    2
    1.11
    is
    1.10
    i
    1.10
    Activations Density 0.050%

    No Known Activations