© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 475
    Prev
    Next
    INDEX
    Explanations

    Seaborn, area, __file__, Searching, Lara

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    y
    0.87
    c
    0.77
    piel
    0.76
    esc
    0.73
     “
    0.73
     Constable
    0.71
    ycin
    0.68
    ’
    0.66
     shirt
    0.66
    ionario
    0.66
    POSITIVE LOGITS
     integrado
    1.03
     aktivitas
    1.02
     jugo
    1.00
     etap
    0.98
     komponen
    0.97
    PARAMETERS
    0.97
    ﻓ
    0.97
    ܠܐ
    0.95
     fluxo
    0.93
    ף
    0.93
    Activations Density 0.000%

    No Known Activations