© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63705
    Prev
    Next
    INDEX
    Explanations

    specific words followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Donate
    0.50
     plantar
    0.48
     donate
    0.46
     doble
    0.46
     சார்ந்த
    0.45
     ischemia
    0.45
     bicycle
    0.45
     receive
    0.44
     Z
    0.44
     Rasmussen
    0.44
    POSITIVE LOGITS
    Strafpunkte
    0.52
    béco
    0.50
    >";
    0.48
     বেশকিছু
    0.48
    ’!
    0.47
    ।’
    0.47
    দিকে
    0.47
    ’-
    0.46
     लॉ
    0.44
    лда
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.