© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7647
    Prev
    Next
    INDEX
    Explanations

    import aliases like cv, ET, args

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     frug
    1.29
    acritic
    1.20
    tif
    1.16
     autonom
    1.15
     accessori
    1.14
    trombone
    1.14
    ᱼ
    1.13
    рыв
    1.13
     (')
    1.12
     nozzles
    1.12
    POSITIVE LOGITS
    ed
    1.07
    过的
    1.00
    back
    0.95
    ar
    0.95
    se
    0.95
    𝘶
    0.95
    quela
    0.92
    part
    0.90
    es
    0.90
    𝘪
    0.90
    Activations Density 0.018%

    No Known Activations