© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81117
    Prev
    Next
    INDEX
    Explanations

    college towns

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

    The neuron selectively activates on the parts of institutional affiliation and location phrases (e.g. “University of…,” “in,” “at,” “Department of…”) that name organizations or places.

    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
     неправи
    -0.77
    precise
    -0.76
     Precise
    -0.75
     precise
    -0.75
     faible
    -0.74
    Kilder
    -0.73
     MethodInfo
    -0.72
    eva
    -0.70
    anyeol
    -0.69
     ErrInvalid
    -0.69
    POSITIVE LOGITS
     Bloomington
    1.23
     Chapel
    1.10
     campus
    1.08
     Gainesville
    1.06
     Urbana
    1.03
     Athens
    1.01
     Ithaca
    0.98
     Madison
    0.98
     Knoxville
    0.95
     Coral
    0.94
    Activations Density 0.083%

    No Known Activations