© 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. 62763
    Prev
    Next
    INDEX
    Explanations

    directional US state names

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

    The neuron detects mentions of colleges and universities (proper names of academic institutions).

    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
     عنه
    -0.74
    Opis
    -0.72
     THEATRE
    -0.71
    Posté
    -0.71
    paciente
    -0.71
    stwie
    -0.70
    ANTAGES
    -0.69
    ñadir
    -0.69
     Кі
    -0.68
     valla
    -0.68
    POSITIVE LOGITS
     Carolina
    0.89
     Illinois
    0.83
    vieto
    0.82
     Michigan
    0.81
     Kentucky
    0.79
    Carolina
    0.78
     Michi
    0.72
     methodical
    0.68
    pla
    0.68
     Mississippi
    0.68
    Activations Density 0.042%

    No Known Activations