© 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. 4601
    Prev
    Next
    INDEX
    Explanations

    using C#

    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
     pera
    1.49
     Phillips
    1.45
    Phillips
    1.38
    chromedriver
    1.38
    ]}{
    1.35
    finder
    1.33
     eyepiece
    1.33
     viewfinder
    1.32
     Clarion
    1.32
     quarry
    1.31
    POSITIVE LOGITS
     všech
    1.09
    垓
    0.98
    malıdır
    0.98
    ูณ
    0.98
    brace
    0.94
    maktadır
    0.94
    arakat
    0.94
    úsc
    0.93
    ισμό
    0.93
    ам
    0.92
    Activations Density 0.027%

    No Known Activations