© 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-16K
    7. 2719
    Prev
    Next
    INDEX
    Explanations

    through

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     afar
    3.18
    t
    2.49
    ባድ
    2.49
    r
    2.36
     whence
    2.30
     segi
    2.25
    𝗦
    2.13
    ки
    2.12
    𝚃
    2.02
     thereon
    2.00
    POSITIVE LOGITS
    ি
    2.03
    ي
    1.87
     مجال
    1.86
    它
    1.85
    犸
    1.79
    ৪৩
    1.77
    iope
    1.76
    নের
    1.73
    则
    1.71
    ವೇ
    1.71
    Activations Density 0.056%

    No Known Activations