© 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. 145508
    Prev
    Next
    INDEX
    Explanations

    staircases and accessibility

    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
     stakeholder
    0.74
     stakeholders
    0.64
    ियो
    0.62
    ou
    0.61
     institution
    0.60
     Winslow
    0.59
    Stake
    0.58
    сай
    0.58
    /
    0.58
    hardware
    0.58
    POSITIVE LOGITS
    cripts
    1.09
     Präsident
    1.05
     Juel
    1.02
     原子
    1.02
     amplitudes
    1.00
     grafts
    1.00
    licting
    0.99
    atching
    0.98
     átomos
    0.98
     tropas
    0.96
    Activations Density 0.000%

    No Known Activations