© 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. 180774
    Prev
    Next
    INDEX
    Explanations

    specific pages

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

    quizzes and urls

    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
     Researcher
    0.47
    થા
    0.47
     ವೀರ
    0.46
    用的
    0.46
     বৃহৎ
    0.45
    ُو
    0.45
     Study
    0.44
    醌
    0.44
    ppable
    0.44
    虽
    0.44
    POSITIVE LOGITS
     sufrimiento
    0.54
    inos
    0.52
     humiliation
    0.50
    iquity
    0.50
    ientos
    0.49
    ќ
    0.49
    entra
    0.48
    unidad
    0.47
    ents
    0.47
     disen
    0.46
    Activations Density 0.000%

    No Known Activations