© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3645
    Prev
    Next
    INDEX
    Explanations

    coastlines, mountains, seas, scenery

    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
    sef
    2.25
    cence
    2.10
    šan
    2.09
     grootste
    1.99
    chy
    1.98
    venta
    1.96
    合法
    1.94
    댔
    1.92
    spedes
    1.90
     PAID
    1.90
    POSITIVE LOGITS
     dw
    1.46
     lain
    1.34
    front
    1.33
    ographique
    1.26
    چه
    1.23
    dwelling
    1.18
    ActionResult
    1.13
    я
    1.13
     dwellers
    1.10
    ناس
    1.08
    Activations Density 0.445%

    No Known Activations