© 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. 212437
    Prev
    Next
    INDEX
    Explanations

    world through, clear as, information purpose, reject any, sent you

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

    Trastevere or asking questions

    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
     sensibil
    0.49
    :
    0.48
    ործ
    0.47
    ла
    0.47
    ł
    0.47
    нина
    0.46
    oxin
    0.45
     puedo
    0.45
     anuncios
    0.45
    فير
    0.44
    POSITIVE LOGITS
    tables
    0.57
    얻
    0.48
     ん
    0.47
     تغییر
    0.47
    dik
    0.46
     ン
    0.46
     جمعیت
    0.45
     میرا
    0.45
    subtract
    0.44
    gheatmap
    0.44
    Activations Density 0.001%

    No Known Activations