© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12519
    Prev
    Next
    INDEX
    Explanations

    monitoring application

    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
    Negative Logits
    𝗺
    2.89
    па
    2.74
    mile
    2.66
    ᴍ
    2.59
     choć
    2.58
    𝐌
    2.55
    ্যাথ
    2.47
     korist
    2.47
    𝕞
    2.45
    Hz
    2.37
    POSITIVE LOGITS
    挲
    4.50
    anwhile
    4.15
    バイル
    4.13
    ামুটি
    3.94
    ificent
    3.81
     Madness
    3.70
    बाईल
    3.57
    gomery
    3.47
     mẽ
    3.43
    achusetts
    3.40
    Activations Density 0.221%

    No Known Activations