© 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. 8221
    Prev
    Next
    INDEX
    Explanations

    only if

    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
    tble
    1.07
     LEC
    0.97
    拯
    0.95
     অঞ্জ
    0.92
    ुलेंस
    0.92
     tble
    0.92
    <unused2150>
    0.92
    廰
    0.91
    userDetail
    0.91
    胝
    0.91
    POSITIVE LOGITS
     or
    0.80
     and
    0.80
    ii
    0.78
    r
    0.73
     be
    0.73
    i
    0.72
     have
    0.71
     is
    0.71
     give
    0.69
     more
    0.68
    Activations Density 0.093%

    No Known Activations