© 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. 10-GEMMASCOPE-RES-131K
    7. 67717
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical supply, liver preservation, USA Hockey

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

    names of places, organizations, and notable entities in news or informational text.

    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_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
     навіть
    -2.69
     حتی
    -2.19
     даже
    -2.11
     even
    -2.08
    Также
    -2.05
     incluso
    -1.98
     também
    -1.95
     також
    -1.94
     sogar
    -1.86
     również
    -1.84
    POSITIVE LOGITS
     andato
    1.84
    hermoso
    1.73
    iempos
    1.73
     venuto
    1.72
    ？（
    1.64
     your
    1.63
    ATUM
    1.63
    ೮
    1.60
    inglés
    1.59
    plata
    1.55
    Activations Density 19.434%

    No Known Activations