© 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. 22-GEMMASCOPE-2-RES-16K
    7. 41
    Prev
    Next
    INDEX
    Explanations

    increase or comparison

    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_22_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
    ጹ
    0.71
    undering
    0.66
     প্রচুর
    0.63
    Nobody
    0.63
     простой
    0.63
     तमाम
    0.62
    nobody
    0.61
     Terrible
    0.61
     enorme
    0.61
     Cheap
    0.60
    POSITIVE LOGITS
     more
    2.87
     lebih
    2.63
     greater
    2.41
    更
    2.38
     better
    2.36
     daha
    2.36
     More
    2.36
     더
    2.33
     hơn
    2.31
     più
    2.30
    Activations Density 5.718%

    No Known Activations