© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4350
    Prev
    Next
    INDEX
    Explanations

    refactor and refine

    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_12_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
    StatusCode
    1.73
    istent
    1.60
     lư
    1.55
     geni
    1.54
     toen
    1.49
     челу
    1.49
     쭉
    1.43
    HLER
    1.41
    댕
    1.40
    стами
    1.39
    POSITIVE LOGITS
    すなわち
    2.16
    urgie
    1.99
    drawing
    1.88
    плення
    1.87
    endale
    1.82
    协商
    1.81
    inner
    1.81
    ське
    1.80
    耽
    1.80
    orda
    1.79
    Activations Density 0.042%

    No Known Activations