© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7050
    Prev
    Next
    INDEX
    Explanations

    replace placeholders

    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_12_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
    Wallpaper
    1.95
    َوْ
    1.88
    ังกฤษ
    1.87
    fony
    1.83
    缛
    1.78
    ILY
    1.74
     Decomposition
    1.73
    ridor
    1.73
    icis
    1.72
    idhi
    1.72
    POSITIVE LOGITS
     neuf
    1.66
    values
    1.61
     fooled
    1.59
     jiv
    1.58
     ¡
    1.57
    anonymous
    1.54
     choisi
    1.53
     اجمعين
    1.52
     values
    1.50
     ایمان
    1.50
    Activations Density 0.007%

    No Known Activations