© 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. 245088
    Prev
    Next
    INDEX
    Explanations

    foreign abbreviations and characters

    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
    ن
    0.48
    方針
    0.45
    を担当
    0.45
    یر
    0.44
     рэгістрацыі
    0.44
    Diabetes
    0.43
    Advertise
    0.43
    綴
    0.42
    atori
    0.42
    bj
    0.42
    POSITIVE LOGITS
     mâ
    0.46
     கைது
    0.46
     、,
    0.45
     vũ
    0.45
     áo
    0.44
     hain
    0.44
    baik
    0.44
     Kush
    0.43
    UZ
    0.42
     பள்ளத்தா
    0.42
    Activations Density 0.000%

    No Known Activations