© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118649
    Prev
    Next
    INDEX
    Explanations

    following conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on Swift “map” closure shorthand syntax—specifically the `{`, the `$` argument names (e.g. `$0`), and the `map` call.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ianto
    -0.72
    request
    -0.68
     computadora
    -0.67
     сказать
    -0.67
     muñeca
    -0.67
     мужчина
    -0.66
    Prijs
    -0.65
     SAY
    -0.65
    Eq
    -0.65
     Estas
    -0.65
    POSITIVE LOGITS
    ynchrotron
    0.79
    legi
    0.70
     healers
    0.70
    '].'
    0.67
     इसका
    0.67
    ադ
    0.66
    bigg
    0.63
     lyss
    0.63
     beverly
    0.63
     cooking
    0.62
    Activations Density 0.068%

    No Known Activations