© 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. 11442
    Prev
    Next
    INDEX
    Explanations

    greeting, function, code execution

    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
    ,
    0.83
    *
    0.81
     weltweit
    0.80
    if
    0.79
    for
    0.77
     Kinder
    0.75
    age
    0.74
    is
    0.74
    er
    0.73
    oder
    0.73
    POSITIVE LOGITS
     ჩატი
    1.53
     utterance
    1.47
     altercation
    1.46
     انا
    1.44
    ㄶ
    1.41
     你
    1.41
     调用
    1.41
     eluted
    1.40
    鼬
    1.40
     jira
    1.39
    Activations Density 0.442%

    No Known Activations