© 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. 25690
    Prev
    Next
    INDEX
    Explanations

    death suggests

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation marks at the end of paragraphs or sentences, particularly periods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    anwal
    -0.94
    特に
    -0.92
    OPIN
    -0.90
    尤其是
    -0.89
    farbe
    -0.88
     футболка
    -0.86
     avancer
    -0.85
    ụp
    -0.85
    姆斯
    -0.85
     shirt
    -0.84
    POSITIVE LOGITS
     so
    1.82
     suggesting
    1.77
     suggests
    1.66
     suggest
    1.54
    说明
    1.52
     indicating
    1.48
    suggest
    1.45
    Clearly
    1.34
     说明
    1.34
     indicates
    1.32
    Activations Density 0.090%

    No Known Activations