© 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. 70037
    Prev
    Next
    INDEX
    Explanations

    Several followed by noun categories

    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
     exceptionally
    -3.02
     unending
    -2.98
     bizarre
    -2.94
     decidedly
    -2.94
     merciless
    -2.81
     '
    -2.80
     continually
    -2.78
    ↵↵
    -2.77
     secluded
    -2.75
     overarching
    -2.72
    POSITIVE LOGITS
    étricas
    3.03
    铼
    2.84
    vantaged
    2.81
    >//
    2.77
    ,’
    2.77
    ftrag
    2.67
    iocene
    2.67
    ﮨ
    2.64
    ensões
    2.64
    ogues
    2.64
    Activations Density 0.026%

    No Known Activations