© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4834
    Prev
    Next
    INDEX
    Explanations

    stared at

    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_17_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
    HtIdx
    1.20
    𒂀
    1.20
    渦柱
    1.20
    𒉕
    1.20
    WMNCA
    1.19
    𒆝
    1.19
    𒆣
    1.19
    <unused2662>
    1.19
    𒅰
    1.19
    testHDR
    1.19
    POSITIVE LOGITS
    com
    0.84
    ,
    0.64
    ne
    0.61
    ss
    0.60
    total
    0.60
     segmented
    0.59
     total
    0.59
    lex
    0.58
     transactions
    0.58
     and
    0.58
    Activations Density 0.001%

    No Known Activations