© 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. 184455
    Prev
    Next
    INDEX
    Explanations

    time, exclude, salon, always, Standardization, can

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

    Executive Summary, manga

    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
     ©️
    0.50
     በ
    0.50
    ৭
    0.48
     Commentaires
    0.48
     perdita
    0.48
     поддержки
    0.47
     экрана
    0.47
    ೭
    0.46
     controladores
    0.46
    ʡ
    0.46
    POSITIVE LOGITS
    ar
    0.47
    templ
    0.42
    aner
    0.41
    tree
    0.40
    عال
    0.40
    ranked
    0.39
    han
    0.38
    erat
    0.37
    م
    0.37
    ta
    0.37
    Activations Density 0.003%

    No Known Activations