© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    XML/HTML tag attributes

    np_acts-logits-general · gemini-2.5-flash-lite

    markup structural tags

    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
    kPa
    0.45
     tiges
    0.44
    renerg
    0.43
    罍
    0.43
    reszt
    0.42
    ilmente
    0.42
    砕
    0.41
    Pitts
    0.41
     milkshake
    0.41
    Piper
    0.41
    POSITIVE LOGITS
     xmlns
    0.73
     />
    0.70
     xsi
    0.68
    ">
    0.65
     type
    0.64
    />
    0.61
    "></
    0.61
    ?>
    0.61
    xmlns
    0.60
     href
    0.56
    Activations Density 0.001%

    No Known Activations