© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68903
    Prev
    Next
    INDEX
    Explanations

    latitude, longitude and degrees

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

    The neuron flags tokens related to longitude coordinate labels or values (e.g. “lng,” “longtitude,” “logtitudes”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     there
    -0.98
     or
    -0.97
     září
    -0.95
     that
    -0.94
    clientY
    -0.94
     when
    -0.93
     while
    -0.93
    روس
    -0.93
    كري
    -0.91
     menyerang
    -0.91
    POSITIVE LOGITS
     corect
    1.06
     Dinas
    1.00
     zaji
    0.97
     ($)
    0.96
     (!!
    0.96
     poe
    0.95
     -.
    0.94
     ,.
    0.93
    vées
    0.93
    Hå
    0.92
    Activations Density 0.023%

    No Known Activations