© 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. 223360
    Prev
    Next
    INDEX
    Explanations

    geographic locations

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

    technical communication and reports

    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
    zte
    0.49
    ay
    0.47
    zie
    0.45
    nte
    0.44
    qin
    0.44
    rio
    0.44
    ost
    0.44
    m
    0.44
    ne
    0.43
    neau
    0.43
    POSITIVE LOGITS
     karşılaş
    0.52
     économique
    0.51
     kullanıl
    0.49
     ব্যবহার
    0.49
    を持つ
    0.48
     Krzysz
    0.48
    ラーメン
    0.48
     utilisés
    0.48
     Polaroid
    0.46
     Gloucester
    0.46
    Activations Density 0.001%

    No Known Activations