© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231729
    Prev
    Next
    INDEX
    Explanations

    join the machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ced
    0.46
     כמה
    0.46
    ="",
    0.45
    xception
    0.45
    >",
    0.44
     ->
    0.44
    cohol
    0.43
    ,*/}
    0.43
    avadoc
    0.43
    render
    0.42
    POSITIVE LOGITS
     Acquisitions
    0.50
     Ip
    0.49
     Zhang
    0.49
    nés
    0.49
     Qi
    0.49
     qi
    0.49
     Maschinen
    0.48
     FIFO
    0.48
     Guangdong
    0.48
     sweatshirts
    0.48
    Activations Density 0.000%

    No Known Activations