© 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. 5736
    Prev
    Next
    INDEX
    Explanations

    data types

    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
    yni
    1.79
    賬
    1.77
    ռ
    1.70
    wicz
    1.70
    ajima
    1.65
    llium
    1.63
     titers
    1.63
    maid
    1.61
     corrective
    1.60
     thác
    1.60
    POSITIVE LOGITS
    argout
    1.40
     Kurn
    1.16
     Siv
    1.15
    PRESSED
    1.13
    ('$
    1.11
     ülk
    1.11
     BHP
    1.10
     hect
    1.10
    (--
    1.08
    Cong
    1.07
    Activations Density 0.002%

    No Known Activations