© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5058
    Prev
    Next
    INDEX
    Explanations

    state of, learning in, it is, car rental, approach to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Nauchno
    1.86
     Wikipédia
    1.78
    <unused2165>
    1.76
    rinsic
    1.74
    hourly
    1.74
     Narod
    1.73
     Titanium
    1.73
     Kelvin
    1.71
     multifunctional
    1.71
     инфра
    1.71
    POSITIVE LOGITS
     arrows
    1.35
     arrow
    1.31
    ↵↵
    1.11
    砷
    1.09
    dler
    1.06
    ertes
    1.06
    ast
    1.04
     strategy
    1.03
     verdict
    1.03
    情节
    1.02
    Activations Density 0.021%

    No Known Activations