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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14479
    Prev
    Next
    INDEX
    Explanations

    US locations and regions

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

    The neuron flags mentions of geographic place names or regional locations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -1.75
     their
    -1.72
     if
    -1.71
     while
    -1.63
     from
    -1.59
     there
    -1.56
     as
    -1.55
     it
    -1.48
     where
    -1.46
     for
    -1.39
    POSITIVE LOGITS
    aktionen
    1.44
     signific
    1.39
     probab
    1.32
    THEN
    1.31
    begins
    1.30
    gante
    1.29
    strecke
    1.28
     ulti
    1.27
    ʃ
    1.27
    скоре
    1.26
    Activations Density 0.092%

    No Known Activations