© 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. 15-GEMMASCOPE-2-RES-16K
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    dive into

    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
    abod
    1.09
    portivo
    0.97
    akur
    0.94
    quilla
    0.94
    Ằ
    0.93
    ItemSelected
    0.92
     creatinine
    0.92
    azada
    0.92
    auc
    0.90
    chre
    0.90
    POSITIVE LOGITS
    σιμοποι
    1.47
    Deploy
    1.42
    !»
    1.41
    닫
    1.39
    裂
    1.39
    訂
    1.39
    锋
    1.39
     Deshalb
    1.38
    ваю
    1.38
    แตก
    1.37
    Activations Density 0.061%

    No Known Activations