© 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. 161726
    Prev
    Next
    INDEX
    Explanations

    Then think, what will, which will

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

    images, figures, or specific content

    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
    Лі
    0.60
    Primero
    0.60
    Дата
    0.57
    𝗱
    0.57
    Про
    0.56
    Mama
    0.55
    Пі
    0.55
    ্ক
    0.55
    За
    0.55
    лії
    0.55
    POSITIVE LOGITS
     wondered
    0.46
    曾经
    0.46
    曾經
    0.45
     omt
    0.42
     Ordnance
    0.42
     \]
    0.40
    思った
    0.40
     eens
    0.40
     histori
    0.40
     Wagen
    0.40
    Activations Density 0.001%

    No Known Activations