© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 16241
    Prev
    Next
    INDEX
    Explanations

    g

    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
    лга
    1.02
    isht
    1.01
    thousand
    1.01
    gha
    1.01
    па
    0.94
    ша
    0.93
     Ш
    0.93
     画像
    0.92
     休
    0.92
    що
    0.91
    POSITIVE LOGITS
     insbesondere
    1.45
     geeignet
    1.42
     einfacher
    1.39
     konie
    1.36
     sowohl
    1.35
     vuoi
    1.32
     záp
    1.29
     gibt
    1.28
     endlich
    1.27
     obiettivo
    1.26
    Activations Density 0.038%

    No Known Activations