© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12148
    Prev
    Next
    INDEX
    Explanations

    Django admin interface

    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_9_width_262k_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
    ic
    1.63
    م
    1.61
    al
    1.49
    ៉
    1.39
    av
    1.33
    ла
    1.33
    im
    1.27
    ме
    1.26
    oct
    1.21
    式
    1.14
    POSITIVE LOGITS
     loafers
    1.45
    examen
    1.40
     Timeout
    1.38
     orchids
    1.35
    දර
    1.35
    잠
    1.35
     时间
    1.34
    Raster
    1.32
    bied
    1.28
    teries
    1.27
    Activations Density 0.001%

    No Known Activations