© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    the word only

    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
    و
    3.76
    nél
    3.70
    er
    3.65
    al
    3.40
    𝔂
    3.29
    ו
    3.21
    zelfde
    2.86
    ू
    2.82
     undoubt
    2.81
    ز
    2.76
    POSITIVE LOGITS
     writ
    3.08
    fans
    2.95
     तभी
    2.95
     foreseeable
    2.84
     лишь
    2.83
    Trashed
    2.83
    ವಲ್ಲ
    2.75
    ሆነ
    2.65
     rarely
    2.59
     partly
    2.58
    Activations Density 0.093%

    No Known Activations