© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6101
    Prev
    Next
    INDEX
    Explanations

    LaTeX math and structure

    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
     ground
    0.74
     [
    0.71
     (
    0.69
     wir
    0.68
     pay
    0.67
    <h1>
    0.67
     Ground
    0.66
    kel
    0.66
     in
    0.66
     a
    0.65
    POSITIVE LOGITS
     aise
    1.12
    <0xA0>
    1.10
    彊
    1.03
     pertanto
    1.01
    嗘
    1.01
     ଚ
    1.00
     transfection
    0.99
     memperoleh
    0.98
    ప్రత్య
    0.98
     promulgating
    0.97
    Activations Density 0.126%

    No Known Activations