© 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. 29015
    Prev
    Next
    INDEX
    Explanations

    products and associated terms

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

    driven by

    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
    ън
    0.52
    梼
    0.49
    ка
    0.48
    ოთ
    0.48
     गवर्नर
    0.48
    กา
    0.47
     caché
    0.47
    гаа
    0.47
    🌬
    0.47
    虢
    0.47
    POSITIVE LOGITS
     সাপ্তাহিক
    0.45
     selectivity
    0.44
    wk
    0.42
     mencionar
    0.41
     discretion
    0.41
     ossia
    0.40
    anz
    0.40
    kw
    0.39
     deaths
    0.39
     impedance
    0.39
    Activations Density 0.000%

    No Known Activations