© 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. 212624
    Prev
    Next
    INDEX
    Explanations

    comparable store, responding to, substituted

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

    adventure and fantasy stories

    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
     банка
    0.49
     instituciones
    0.48
    聁
    0.48
     магазина
    0.47
    ınca
    0.47
     retiring
    0.46
     প্রতিষ্ঠান
    0.46
    ą
    0.45
    quitos
    0.44
    creational
    0.44
    POSITIVE LOGITS
     ಕಂಡು
    0.45
     käs
    0.44
     erythro
    0.43
    見る
    0.43
    郢
    0.42
     ELSE
    0.40
     else
    0.40
     കണ്ട
    0.39
     mesto
    0.39
     Else
    0.39
    Activations Density 0.001%

    No Known Activations