© 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-65K
    7. 2116
    Prev
    Next
    INDEX
    Explanations

    actions and movements

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     powertrain
    0.71
    absorbing
    0.67
     subjekt
    0.66
    楽しみ
    0.66
     Convolution
    0.65
     SaaS
    0.65
    遐
    0.64
    回合
    0.64
    Ghost
    0.64
     metaverse
    0.63
    POSITIVE LOGITS
     climbed
    1.06
     hauling
    0.92
     climbing
    0.91
     climb
    0.90
     barric
    0.88
     tied
    0.87
     hoisting
    0.86
     carrying
    0.85
     climbs
    0.85
     throwing
    0.85
    Activations Density 0.242%

    No Known Activations