© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    GTA and similar games

    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
    REETYPE
    2.21
    ্য
    2.06
     parcial
    1.99
    る
    1.97
    ΟΥ
    1.95
    ্তা
    1.93
    ned
    1.93
    ಿ
    1.91
    嵋
    1.88
    ed
    1.88
    POSITIVE LOGITS
    챔
    2.11
    ษฐ
    2.11
     bezpiecze
    2.10
    ኋላ
    2.09
    ీ
    2.08
    __(/*!
    2.06
    spers
    2.04
    चलिए
    2.01
    mical
    2.00
     zak
    1.98
    Activations Density 0.025%

    No Known Activations