© 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. 15-GEMMASCOPE-2-RES-16K
    7. 2608
    Prev
    Next
    INDEX
    Explanations

    location or previous mention

    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
     الفرنسي
    1.76
    ادرة
    1.58
    uja
    1.55
    ולד
    1.55
     distributing
    1.50
    ajt
    1.50
     vindt
    1.47
    ẵ
    1.46
    день
    1.42
     constater
    1.41
    POSITIVE LOGITS
     above
    2.44
     below
    2.37
    above
    2.31
    below
    2.17
     acima
    2.16
     previously
    2.05
     earlier
    2.04
     herein
    1.98
     ABOVE
    1.97
     bellow
    1.96
    Activations Density 0.200%

    No Known Activations