© 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. 195819
    Prev
    Next
    INDEX
    Explanations

    international or obscure words

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

    classification and description

    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
     to
    0.50
    ួក
    0.49
     lingering
    0.49
    ಪಟ್ಟ
    0.46
    消防
    0.46
    🚒
    0.45
    レイン
    0.45
     sailors
    0.45
     soulful
    0.45
     gifting
    0.44
    POSITIVE LOGITS
    eszcze
    0.59
    ässig
    0.46
    媑
    0.46
    aschen
    0.46
    öss
    0.46
    odom
    0.45
    ər
    0.45
    askell
    0.45
     kæ
    0.44
     Substances
    0.44
    Activations Density 0.001%

    No Known Activations