© 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. 10884
    Prev
    Next
    INDEX
    Explanations

    conclusions and therefore

    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
    Not in Any Lists

    No Comments

    Negative Logits
     change
    0.73
     difference
    0.73
     remaining
    0.68
     manual
    0.68
     pressure
    0.64
    s
    0.62
     Manual
    0.61
    difference
    0.59
     monthly
    0.59
     numbers
    0.58
    POSITIVE LOGITS
    hydes
    1.01
    𝐘
    0.98
     teorías
    0.96
    উন্ড
    0.93
     teoría
    0.92
     теория
    0.92
     szpital
    0.91
    çado
    0.90
     rispond
    0.89
     jeżeli
    0.89
    Activations Density 0.000%

    No Known Activations