© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9323
    Prev
    Next
    INDEX
    Explanations

    companion, accompaniment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    س
    2.95
    د
    2.74
    ط
    2.61
    তা
    2.56
    amic
    2.52
    கள்
    2.50
    તિ
    2.46
    ями
    2.34
    ста
    2.32
    ních
    2.31
    POSITIVE LOGITS
    侶
    3.21
     regard
    3.19
    ే
    3.13
    NSLog
    3.12
    侣
    3.10
    뎐
    2.79
     heartbreak
    2.75
     `${
    2.72
    ModelAndView
    2.70
     KB
    2.70
    Activations Density 0.016%

    No Known Activations