© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6382
    Prev
    Next
    INDEX
    Explanations

    json output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    AsAction
    1.40
     eyed
    1.38
     fenómeno
    1.36
     ángulo
    1.33
    <unused2112>
    1.33
     cytokine
    1.33
    methoxy
    1.33
     tearing
    1.30
    掰
    1.29
    肌肉
    1.29
    POSITIVE LOGITS
     Bray
    1.30
    ha
    1.30
    ща
    1.29
    冀
    1.24
    уы
    1.24
     "
    1.23
     Архив
    1.22
     (/
    1.22
    ['
    1.21
    explore
    1.21
    Activations Density 0.002%

    No Known Activations