© 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. 16-GEMMASCOPE-2-RES-262K
    7. 142362
    Prev
    Next
    INDEX
    Explanations

    specific categories and terms

    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_16_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
     auk
    0.49
     outlay
    0.49
     ad
    0.46
    OL
    0.46
    BeforeText
    0.46
    ז
    0.45
    봐
    0.45
    ıyor
    0.45
    vider
    0.44
    Beverungen
    0.43
    POSITIVE LOGITS
     ры
    0.57
     ဒါ
    0.55
    ры
    0.50
     différence
    0.49
    ない
    0.49
     regrettable
    0.49
    轆
    0.49
    ᅵ
    0.48
     σχέ
    0.48
    盃
    0.48
    Activations Density 0.000%

    No Known Activations