© 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. 100967
    Prev
    Next
    INDEX
    Explanations

    verbs and their forms

    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
    轂
    -1.46
    Nikon
    -1.45
    zzly
    -1.41
    歼
    -1.41
    גון
    -1.41
    exemple
    -1.41
    pptx
    -1.38
    Recher
    -1.38
    Parce
    -1.36
    Pourquoi
    -1.34
    POSITIVE LOGITS
     other
    2.27
     also
    2.13
     for
    1.72
     Not
    1.71
     Other
    1.68
     others
    1.65
     as
    1.63
     This
    1.49
     in
    1.48
     For
    1.45
    Activations Density 0.071%

    No Known Activations