© 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. 129270
    Prev
    Next
    INDEX
    Explanations

    case names or Q: followed by subjects

    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
    Cuánto
    -1.51
     וכן
    -1.48
     sudadera
    -1.45
    ॑
    -1.41
    もうすぐ
    -1.39
    Этот
    -1.39
     Aseg
    -1.38
    お疲れ
    -1.35
     goederen
    -1.34
    暱
    -1.34
    POSITIVE LOGITS
    があり
    1.50
    <>
    1.49
    なので
    1.38
    no
    1.35
    子は
    1.33
     (
    1.33
    st
    1.29
    >
    1.29
    _
    1.29
     –
    1.28
    Activations Density 0.000%

    No Known Activations