© 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-16K
    7. 1733
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_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
    鐒
    3.00
    ാ
    2.96
    ولة
    2.94
    an
    2.93
     campaigned
    2.89
    ो
    2.84
    اس
    2.82
    umal
    2.79
    ுமி
    2.75
    но
    2.70
    POSITIVE LOGITS
    t
    3.97
     koje
    2.94
     уважаемые
    2.71
    स
    2.70
    <unused2127>
    2.68
    Myanmar
    2.68
    有
    2.68
     Humans
    2.66
    ように
    2.65
     које
    2.63
    Activations Density 0.683%

    No Known Activations