© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58478
    Prev
    Next
    INDEX
    Explanations

    biggest growth

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

    elementary school

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ચે
    0.56
     সবকিছু
    0.50
     solicitado
    0.48
    燦
    0.46
     Cheshire
    0.46
     जरिए
    0.45
     ści
    0.45
    Crypto
    0.45
    FT
    0.43
     Kiev
    0.43
    POSITIVE LOGITS
    aun
    0.46
    ных
    0.43
    ర
    0.43
    үл
    0.43
    amaks
    0.43
     dermatology
    0.42
     Dermatology
    0.42
    müş
    0.42
    ments
    0.41
     murders
    0.41
    Activations Density 0.000%

    No Known Activations