© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1896
    Prev
    Next
    INDEX
    Explanations

    waste disposal and decluttering

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

    religious discourse and commandments

    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
    </h2>
    0.25
     erg
    0.23
    text
    0.23
     text
    0.22
     ligands
    0.22
    affiliation
    0.22
    ้าย
    0.22
    ϭ
    0.22
    assert
    0.22
     बाध्य
    0.22
    POSITIVE LOGITS
     экологи
    0.27
    蝴蝶
    0.27
     Celebrate
    0.26
     Butterflies
    0.25
     रिश्
    0.25
     Environmental
    0.25
     ζωή
    0.25
     yaşayan
    0.25
     생활
    0.25
    Environmental
    0.24
    Activations Density 0.044%

    No Known Activations