© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    educational and informational websites

    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
    س
    2.04
    ez
    1.96
    ت
    1.95
    বাল
    1.83
    చ
    1.81
    er
    1.73
    itsi
    1.72
    hose
    1.72
    ى
    1.70
    ுடன்
    1.65
    POSITIVE LOGITS
     MATTER
    2.09
     matter
    2.04
    hesians
    2.01
     아멘
    1.95
    regarded
    1.93
    พันธ์
    1.92
    matter
    1.92
    னித
    1.92
     coveted
    1.90
     expires
    1.89
    Activations Density 0.100%

    No Known Activations