© 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. 6456
    Prev
    Next
    INDEX
    Explanations

    exercise repetitions

    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
    poder
    1.64
    stö
    1.62
    년간
    1.61
    unnumbered
    1.59
    ∼
    1.58
    arl
    1.52
    ení
    1.51
     tới
    1.51
    <0xEA>
    1.50
    maa
    1.49
    POSITIVE LOGITS
    Lif
    1.09
    asin
    1.07
    揩
    0.95
    ライズ
    0.95
    化工
    0.92
     ښ
    0.92
    ⺈
    0.91
     zain
    0.91
    оборот
    0.91
     sanitary
    0.90
    Activations Density 0.022%

    No Known Activations