© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9630
    Prev
    Next
    INDEX
    Explanations

    conferences and meetings

    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
     possibility
    2.73
    pairwise
    2.61
    특별시
    2.52
     electrop
    2.51
    //*[@
    2.43
     infotainment
    2.34
     tortoises
    2.33
     Navier
    2.33
     enshr
    2.31
    р
    2.28
    POSITIVE LOGITS
    er
    3.81
    jší
    3.36
    ти
    2.74
    e
    2.72
    siniz
    2.69
    liel
    2.69
    eze
    2.66
    ClCompile
    2.60
    ྛ
    2.58
    erende
    2.56
    Activations Density 0.076%

    No Known Activations