© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19124
    Prev
    Next
    INDEX
    Explanations

    event followed by description

    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
    vantaged
    -2.58
    however
    -2.16
    ghalaya
    -2.14
    of
    -2.11
     emphatic
    -2.08
    愎
    -2.08
     homage
    -2.03
    쏴
    -2.03
    diseño
    -2.02
    不必
    -2.00
    POSITIVE LOGITS
    g
    2.59
    tômes
    2.48
     dengan
    2.48
    
    2.33
    t
    2.33
    ྜ
    2.33
    是很
    2.30
    नलोड
    2.28
     With
    2.27
     soo
    2.23
    Activations Density 0.020%

    No Known Activations