© 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-65K
    7. 8655
    Prev
    Next
    INDEX
    Explanations

    non-numeric, non-technical, non-oil

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ethical
    0.85
     ethics
    0.82
     any
    0.81
     qualsiasi
    0.76
     uncontrolled
    0.75
     athe
    0.75
     entanglement
    0.75
     Una
    0.75
     iemand
    0.74
    ఖ
    0.74
    POSITIVE LOGITS
    Le
    0.88
    replace
    0.86
    Carrie
    0.84
    Leo
    0.83
    Replace
    0.83
    We
    0.79
    Cas
    0.77
    Gas
    0.77
    Core
    0.76
    Compute
    0.76
    Activations Density 0.030%

    No Known Activations