© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11263
    Prev
    Next
    INDEX
    Explanations

    don't owe explanations

    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
     ​
    2.33
    ​.
    1.98
    monium
    1.92
     ‍
    1.84
     उन्‍ह
    1.79
     foundational
    1.78
    oncé
    1.78
     ✔
    1.77
     Ranch
    1.77
     OSError
    1.76
    POSITIVE LOGITS
     دائما
    2.03
     måle
    1.93
    StopTime
    1.92
     stov
    1.88
     jaga
    1.87
    getX
    1.86
     och
    1.86
    ть
    1.82
    obs
    1.80
     prestazioni
    1.80
    Activations Density 0.019%

    No Known Activations