© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14074
    Prev
    Next
    INDEX
    Explanations

    `grep -o`

    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_13_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
    𒆝
    1.46
    𒌾
    1.46
    渦柱
    1.46
    HtIdx
    1.46
    𒂀
    1.46
     vuccatiti
    1.45
    𒈖
    1.45
    𒋭
    1.45
    𒂤
    1.45
    𒆣
    1.45
    POSITIVE LOGITS
    1.24
     (
    0.94
     *
    0.90
     "
    0.88
     Sh
    0.82
     О
    0.80
     painful
    0.79
     “
    0.78
     harsh
    0.78
     concerning
    0.78
    Activations Density 0.001%

    No Known Activations