© 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. 1012
    Prev
    Next
    INDEX
    Explanations

    code output and variables

    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
    উল
    0.63
    awatir
    0.61
     뒷
    0.57
    νό
    0.56
     riti
    0.55
     Villar
    0.55
    slit
    0.52
    rient
    0.52
    apour
    0.52
     culprits
    0.52
    POSITIVE LOGITS
     await
    0.82
    using
    0.75
     Pray
    0.75
    $"
    0.74
    var
    0.74
    ิ้ง
    0.73
     yath
    0.72
     USING
    0.71
    araham
    0.71
    ями
    0.71
    Activations Density 0.269%

    No Known Activations