© 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. 12310
    Prev
    Next
    INDEX
    Explanations

    search queries or instructions

    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
    ⋙
    1.42
    ার
    1.36
     printr
    1.32
    Guided
    1.26
    Consequently
    1.25
    
    1.25
    er
    1.24
     HttpException
    1.24
    Então
    1.24
    𒆪
    1.24
    POSITIVE LOGITS
    iguë
    1.24
     stairs
    1.14
     cabinets
    1.09
     wheels
    1.02
     cabinetry
    1.00
    ek
    1.00
     tubs
    0.98
     каждому
    0.98
     cour
    0.97
    িকের
    0.96
    Activations Density 0.000%

    No Known Activations