© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    website/webpage structure

    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
     Hempstead
    1.48
    で使用
    1.47
    стно
    1.45
    پیش
    1.43
    рного
    1.42
    込
    1.42
     Zam
    1.40
    emeen
    1.39
    では
    1.39
     المقد
    1.38
    POSITIVE LOGITS
    nat
    1.05
    ature
    0.96
    organisms
    0.86
    Late
    0.85
    nate
    0.82
    lungs
    0.80
    }<
    0.80
    physics
    0.78
    from
    0.77
     stung
    0.77
    Activations Density 0.014%

    No Known Activations