© 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. 2663
    Prev
    Next
    INDEX
    Explanations

    department and sector classifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    क
    3.00
    
    2.80
    ု
    2.47
    е
    2.47
     käyt
    2.32
    켈
    2.29
    
    2.27
    
    2.27
     расс
    2.25
    ВО
    2.21
    POSITIVE LOGITS
    ش
    3.80
    ierung
    2.81
     complémentaires
    2.77
    有助于
    2.76
    علم
    2.71
    こと
    2.68
    மேலும்
    2.60
    ות
    2.60
    𝙧
    2.58
    enie
    2.53
    Activations Density 0.307%

    No Known Activations