© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9227
    Prev
    Next
    INDEX
    Explanations

    tables with structured data

    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_22_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
    <0xAB>
    1.16
     joyful
    1.08
     Society
    1.08
    society
    1.07
     Loy
    1.07
     lon
    1.06
     SOCIETY
    1.05
     Kov
    1.05
    恋
    1.02
    गन
    1.02
    POSITIVE LOGITS
    http
    1.85
     http
    1.75
    ttp
    1.37
     www
    1.29
    www
    1.27
    https
    1.14
    mathrm
    1.09
     htt
    1.05
     https
    1.04
     httpRequest
    1.03
    Activations Density 0.073%

    No Known Activations