© 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. 84120
    Prev
    Next
    INDEX
    Explanations

    Paul, pcs, publication, chance, camera, child

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

    date, exam, critical, information

    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
    ر
    0.47
    stücke
    0.46
    сма
    0.45
    强烈
    0.44
     кнопки
    0.43
     тре
    0.42
    यास
    0.42
    كَ
    0.42
    сть
    0.42
    γεν
    0.42
    POSITIVE LOGITS
     presupuesto
    0.50
     fascist
    0.48
     insists
    0.47
     observado
    0.47
     Министерство
    0.46
     budgets
    0.46
     trabajado
    0.46
     subside
    0.46
     evaporates
    0.46
    !”
    0.46
    Activations Density 0.002%

    No Known Activations