© 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. 29-GEMMASCOPE-2-RES-65K
    7. 1927
    Prev
    Next
    INDEX
    Explanations

    Quebec H postal codes

    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_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     erc
    0.94
     cnc
    0.89
     tds
    0.88
    vdd
    0.84
     cfp
    0.82
     pwm
    0.81
     dxf
    0.81
    ﾔ
    0.80
     qa
    0.80
     edt
    0.79
    POSITIVE LOGITS
     B
    2.53
    B
    2.35
     D
    2.33
     E
    2.25
     C
    2.18
    D
    2.12
    E
    2.03
    C
    2.02
     F
    2.00
     G
    1.95
    Activations Density 0.877%

    No Known Activations