© 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. 12354
    Prev
    Next
    INDEX
    Explanations

    the concept of

    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
     veamos
    2.65
     voork
    2.61
     erfolgt
    2.57
     periód
    2.55
    โมง
    2.48
    据悉
    2.44
     başta
    2.40
    
    2.38
    त
    2.32
    Д
    2.31
    POSITIVE LOGITS
    een
    2.69
    ዖ
    2.67
    ++++
    2.63
     bathed
    2.53
    ът
    2.53
    tedir
    2.47
    aronne
    2.37
    iteten
    2.35
    領
    2.35
    ゆる
    2.33
    Activations Density 0.165%

    No Known Activations