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

    Neuronpedia

    Jacobian LensNEW
    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. 1870
    Prev
    Next
    INDEX
    Explanations

    explain, example, exhaust, your mind

    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
    roz
    0.64
     opérations
    0.62
     rij
    0.57
     শাস্ত্র
    0.57
    <0xA0>
    0.57
    urale
    0.56
    呼び
    0.56
    몰
    0.56
    bres
    0.56
     ropes
    0.55
    POSITIVE LOGITS
    peh
    0.71
     Dah
    0.58
     ڈھ
    0.57
     өчен
    0.57
    pah
    0.56
     Park
    0.55
    Hal
    0.55
     Pie
    0.55
     huh
    0.55
     अल्फा
    0.54
    Activations Density 0.309%

    No Known Activations