© 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-16K
    7. 3409
    Prev
    Next
    INDEX
    Explanations

    Digital/pixel concepts followed by titles

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     comprehensive
    0.78
     macroeconomic
    0.76
    IBM
    0.75
     umfass
    0.75
     summarized
    0.74
     strategic
    0.73
    Comprehensive
    0.72
     technical
    0.72
     বহুম
    0.71
    🔟
    0.71
    POSITIVE LOGITS
    乐队
    1.14
     oscuridad
    1.08
     Riot
    1.04
     Remix
    1.04
     Stereo
    1.03
     remix
    1.02
     Ruins
    1.00
     overdose
    1.00
    soaked
    0.99
     Punk
    0.95
    Activations Density 0.404%

    No Known Activations