© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4288
    Prev
    Next
    INDEX
    Explanations

    stylesheet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     títulos
    0.43
     boutons
    0.41
    Titles
    0.40
     langue
    0.39
     বৈঠ
    0.38
    量
    0.37
     Kwa
    0.37
     эффек
    0.37
    Kwa
    0.37
    ܢ
    0.37
    POSITIVE LOGITS
    stylesheet
    1.03
    icon
    0.74
    shortcut
    0.73
    preconnect
    0.71
    canonical
    0.65
     stylesheet
    0.64
    apple
    0.63
    Stylesheet
    0.62
    SHORT
    0.61
     shortcut
    0.59
    Activations Density 0.001%

    No Known Activations