© 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. 5998
    Prev
    Next
    INDEX
    Explanations

    the discussion of cases

    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
    ്യ
    0.75
    ちな
    0.73
    𝙫
    0.72
     شوي
    0.71
    şık
    0.70
    šť
    0.70
    ゥ
    0.70
    ጃ
    0.67
     some
    0.67
    ោង
    0.66
    POSITIVE LOGITS
     case
    1.14
    Case
    1.12
     Case
    1.01
     words
    1.00
    CASE
    0.81
     palabras
    0.81
     caso
    0.81
    言葉
    0.78
     CASE
    0.77
    case
    0.76
    Activations Density 0.000%

    No Known Activations