© 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. 6899
    Prev
    Next
    INDEX
    Explanations

    tailoring

    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
     җ
    2.35
    年
    2.08
    Starburst
    2.00
     ویکی‌پ
    2.00
     chiếu
    2.00
    чество
    1.97
    aczego
    1.92
    STIC
    1.92
    ارة
    1.91
    áticamente
    1.88
    POSITIVE LOGITS
    \%$
    1.54
    rolog
    1.54
    rop
    1.46
    urier
    1.45
    riteria
    1.45
     ;$
    1.45
    ハウス
    1.44
     Plante
    1.44
    uia
    1.43
     început
    1.40
    Activations Density 0.271%

    No Known Activations