© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    language model creation

    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
     recommending
    0.86
    जनन
    0.84
     Securities
    0.82
    灭
    0.82
     stalking
    0.81
    띵
    0.80
     relating
    0.79
     Knows
    0.78
     MEMBER
    0.77
     দিক
    0.77
    POSITIVE LOGITS
    प्रति
    0.70
    수의
    0.68
    ство
    0.67
    ची
    0.63
    с
    0.63
    dari
    0.61
    anova
    0.60
     घरी
    0.60
     Large
    0.60
     balle
    0.59
    Activations Density 0.010%

    No Known Activations