© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3294
    Prev
    Next
    INDEX
    Explanations

    video content

    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_29_width_65k_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
     Docket
    0.64
     ترقی
    0.64
    ReadLine
    0.61
    柄
    0.61
    гази
    0.60
     തൂ
    0.60
     tabpos
    0.59
     forbind
    0.59
    辐
    0.58
     अंका
    0.58
    POSITIVE LOGITS
     videos
    4.73
     video
    4.62
     Videos
    4.32
     Video
    4.25
    视频
    4.23
     видео
    4.23
    Video
    4.21
    video
    4.17
    Videos
    4.10
    videos
    4.05
    Activations Density 0.663%

    No Known Activations