© 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. 29-GEMMASCOPE-2-RES-262K
    7. 145573
    Prev
    Next
    INDEX
    Explanations

    walk around specific locations

    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_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ทุน
    0.90
    "'
    0.79
    deren
    0.74
     Livingstone
    0.72
    ダー
    0.70
    ക്കാരി
    0.69
    ."'
    0.68
     sucesivamente
    0.68
    slide
    0.68
    錢
    0.67
    POSITIVE LOGITS
     ocz
    0.81
     Jaw
    0.79
     온
    0.75
     реак
    0.74
     Thanks
    0.72
     Runs
    0.71
     Run
    0.70
     issue
    0.70
     own
    0.70
     Issuer
    0.69
    Activations Density 0.001%

    No Known Activations