© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    why questions or specific numerical patterns

    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_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     warfare
    1.07
     festivities
    1.05
     sensibilities
    1.02
     accessories
    1.01
     superstit
    1.00
     narratives
    0.97
     royalties
    0.97
    🔯
    0.96
     territories
    0.96
     unscrupulous
    0.96
    POSITIVE LOGITS
    0
    1.36
    2
    1.27
    1
    1.22
    4
    1.21
    5
    1.16
    3
    1.12
    6
    1.08
    9
    1.01
    7
    1.00
    Calculation
    0.98
    Activations Density 0.000%

    No Known Activations