© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13988
    Prev
    Next
    INDEX
    Explanations

    turkey roasting

    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_7_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
    anju
    2.61
    huana
    2.33
    พาะ
    2.32
    </tbody>
    2.31
    kau
    2.30
    rza
    2.27
    yta
    2.26
    স্থাপন
    2.19
    ͯ
    2.18
    ters
    2.18
    POSITIVE LOGITS
    ுள்ள
    3.09
    ો
    2.80
    iglio
    2.35
    忡
    2.30
    ead
    2.29
    dine
    2.29
     tercero
    2.28
     shove
    2.27
    েশন
    2.27
    urilor
    2.26
    Activations Density 0.001%

    No Known Activations