© 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. 26256
    Prev
    Next
    INDEX
    Explanations

    enclosure or enclosing

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

    enclosed, sit, stand, want, aims

    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
    pozy
    0.57
    ០
    0.57
    ayad
    0.53
    isimple
    0.50
    forderungen
    0.48
    kon
    0.48
    frow
    0.48
    ṇ
    0.48
    ukar
    0.48
    bon
    0.47
    POSITIVE LOGITS
     enclosures
    0.53
    ил
    0.48
     enclosure
    0.47
     encerr
    0.46
     encir
    0.44
     recinto
    0.43
     regulate
    0.42
    ILD
    0.41
     beetles
    0.41
    ల
    0.41
    Activations Density 0.000%

    No Known Activations