© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    directory path operations

    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
    anden
    1.18
    [][]
    0.97
     watering
    0.94
    établ
    0.87
     denominated
    0.87
     grille
    0.84
    imported
    0.84
    geben
    0.83
    匁
    0.83
    濯
    0.82
    POSITIVE LOGITS
     seit
    1.81
     Steinberg
    1.60
     ближай
    1.59
     jüng
    1.57
    寻
    1.56
     sejak
    1.55
     perto
    1.54
     eş
    1.52
     поиск
    1.52
     znak
    1.52
    Activations Density 0.010%

    No Known Activations