© 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. 22-GEMMASCOPE-RES-131K
    7. 130234
    Prev
    Next
    INDEX
    Explanations

    negation or absence

    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
     lidé
    -1.10
    исленность
    -1.03
    もあった
    -0.92
     properly
    -0.90
     Properly
    -0.90
    VolleyError
    -0.89
    Portug
    -0.86
    cussion
    -0.86
     quieran
    -0.85
    telsen
    -0.85
    POSITIVE LOGITS
     using
    0.98
    使用
    0.90
     trying
    0.90
     expecting
    0.88
     hinzufügen
    0.85
    需要
    0.82
     exacerb
    0.78
     仁
    0.78
    confirmButton
    0.77
     involve
    0.77
    Activations Density 0.051%

    No Known Activations