© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2154
    Prev
    Next
    INDEX
    Explanations

    positive integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     ecuaciones
    0.99
     chromedp
    0.96
     geniş
    0.96
     brinqu
    0.93
     ήταν
    0.92
     девя
    0.92
     είναι
    0.92
    =(\
    0.91
     반지름
    0.90
     paysans
    0.90
    POSITIVE LOGITS
     specific
    0.81
     specifically
    0.70
     certain
    0.67
    それ
    0.66
     some
    0.65
    specific
    0.65
    itory
    0.64
     preventing
    0.63
    orea
    0.62
     ا
    0.62
    Activations Density 0.001%

    No Known Activations