© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10917
    Prev
    Next
    INDEX
    Explanations

    AB, LA, col

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    lass
    2.08
    ning
    2.04
    了
    1.96
     intellig
    1.94
     vistas
    1.93
    ned
    1.91
     the
    1.90
    та
    1.89
    óst
    1.88
     eng
    1.88
    POSITIVE LOGITS
    जनबी
    2.56
    צים
    2.43
    حدیث
    2.30
    Dopo
    2.29
    ี่ยง
    2.29
    <bos>
    2.23
    ğ
    2.21
    REQ
    2.15
    ğa
    2.15
    ehl
    2.14
    Activations Density 0.033%

    No Known Activations