© 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. 34-GEMMASCOPE-RES-131K
    7. 31403
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations and dates

    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_34/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
    恺
    -0.75
     HIM
    -0.75
    GPI
    -0.74
    ंच
    -0.73
    estras
    -0.71
     Bain
    -0.69
     services
    -0.68
    experiment
    -0.68
     Christen
    -0.68
    Acquire
    -0.68
    POSITIVE LOGITS
     conson
    0.94
     RSV
    0.88
     scholarly
    0.84
     Ug
    0.83
    DDD
    0.81
     ETS
    0.81
     LXX
    0.81
    Insee
    0.81
     minimalism
    0.80
     ל
    0.78
    Activations Density 0.031%

    No Known Activations