© 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. 5588
    Prev
    Next
    INDEX
    Explanations

    slow down

    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
     ಹು
    0.76
     ഉപ
    0.74
    헤
    0.73
    入れる
    0.73
     stá
    0.69
    অন্ত
    0.68
     leasing
    0.68
    でお
    0.66
    ৗ
    0.66
     Eastern
    0.65
    POSITIVE LOGITS
     down
    3.11
     Down
    2.70
    down
    2.63
    Down
    2.51
     DOWN
    2.37
    DOWN
    2.05
    downs
    1.99
    ダウン
    1.80
     डाउन
    1.76
     downs
    1.74
    Activations Density 0.125%

    No Known Activations