© 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. 233574
    Prev
    Next
    INDEX
    Explanations

    pat or pet words

    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
    ونها
    0.58
    \">
    0.57
    楔
    0.54
    ون
    0.53
     pries
    0.52
     Rit
    0.51
     Rishi
    0.51
     Ceb
    0.51
    '}}>
    0.51
    入射
    0.50
    POSITIVE LOGITS
    pet
    0.69
    pat
    0.68
     patrons
    0.66
     пет
    0.63
    Pat
    0.62
     પેટ
    0.61
     pet
    0.60
    patri
    0.60
     Patron
    0.57
     পেট্র
    0.57
    Activations Density 0.146%

    No Known Activations