© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12206
    Prev
    Next
    INDEX
    Explanations

    py, ly, my, sy prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    Signin
    2.65
    ,,,,
    2.56
    Live
    2.52
    __(/*!
    2.48
     Live
    2.41
     birth
    2.23
    ിക്ക
    2.21
    mort
    2.20
    ിക
    2.19
    ியில்
    2.17
    POSITIVE LOGITS
    vonne
    3.54
    outube
    3.37
    ോഗ്യ
    3.35
    yyyyyyyy
    3.29
    麼
    3.04
    esterday
    2.98
    ोजक
    2.90
    yyyy
    2.86
    ूरिया
    2.78
    untamiento
    2.78
    Activations Density 1.880%

    No Known Activations