© 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. 10941
    Prev
    Next
    INDEX
    Explanations

    healthcare professional

    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
    ECTION
    2.08
    ••
    1.86
    度が
    1.80
    渀
    1.75
     tiling
    1.75
    መን
    1.75
     junction
    1.73
     phare
    1.72
    猀
    1.71
     primary
    1.67
    POSITIVE LOGITS
    烺
    2.36
    jdbc
    2.35
    ヂストン
    2.20
    alek
    2.19
     deduct
    2.16
    َم
    2.16
     ощущения
    2.16
    揺
    2.13
    슘
    2.12
    ي
    2.11
    Activations Density 0.055%

    No Known Activations