© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 11588
    Prev
    Next
    INDEX
    Explanations

    technical keywords and subsequent terms

    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
     "
    0.60
      
    0.60
     this
    0.58
    0.56
     another
    0.53
     code
    0.53
     next
    0.52
    ("#
    0.52
    0.51
    p
    0.51
    POSITIVE LOGITS
    ష్య
    1.05
     incision
    0.99
     redox
    0.97
     melakukannya
    0.96
     menino
    0.96
    __'
    0.96
    юнча
    0.95
    ┇
    0.95
     सूफ़ी
    0.94
     tomonidan
    0.93
    Activations Density 0.010%

    No Known Activations