© 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. 4974
    Prev
    Next
    INDEX
    Explanations

    response and replies

    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
     textured
    1.19
     경제
    1.18
    buttonBar
    1.15
     pots
    1.15
     spf
    1.14
     wellness
    1.13
     nutrient
    1.13
    鼕
    1.11
    <unused517>
    1.11
    <unused895>
    1.11
    POSITIVE LOGITS
    ide
    0.93
    ição
    0.89
    ides
    0.85
    คืน
    0.83
    side
    0.81
    iaire
    0.78
    iria
    0.76
    Carousel
    0.74
    となります
    0.74
    貴
    0.73
    Activations Density 0.126%

    No Known Activations