© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6539
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    elaide
    1.25
    ห์
    1.18
     Palmy
    1.13
    jem
    1.08
    ogly
    1.04
    oglycos
    1.02
    (=
    1.02
    PHIL
    1.01
    lict
    1.00
    éis
    1.00
    POSITIVE LOGITS
     кор
    1.83
    废水
    1.75
    Floor
    1.73
     moss
    1.72
    Wax
    1.71
     бю
    1.71
    Mamm
    1.71
     Wax
    1.68
     Barkley
    1.68
    ]["
    1.66
    Activations Density 0.001%

    No Known Activations