© 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. 29985
    Prev
    Next
    INDEX
    Explanations

    is composed of

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

    This neuron detects capitalized proper-name tokens, especially those in named landmarks or building titles.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    alnız
    -0.91
     old
    -0.91
     our
    -0.88
     piccola
    -0.84
    msgstr
    -0.84
    malade
    -0.82
    WebElementEntity
    -0.81
     small
    -0.81
     памят
    -0.81
     sederhana
    -0.80
    POSITIVE LOGITS
     glass
    1.16
     LED
    1.08
     giant
    1.07
     designers
    1.06
     gigantic
    1.05
     steel
    1.04
     futuristic
    1.04
     stainless
    1.02
     bijzondere
    0.98
     structural
    0.97
    Activations Density 0.043%

    No Known Activations