© 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. 10-GEMMASCOPE-RES-131K
    4. 130761
    Prev
    Next
    INDEX
    Explanations

    geographical regions

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

    The neuron fires on place names or regional geographic terms (e.g., country, state, or area names).

    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
    嗫
    -1.41
    following
    -1.40
     другое
    -1.39
     tentando
    -1.38
     organisme
    -1.36
     faciliter
    -1.35
     coreano
    -1.35
     erforderlichen
    -1.34
     créer
    -1.34
     murale
    -1.34
    POSITIVE LOGITS
     with
    2.19
     for
    2.11
     at
    1.72
     through
    1.65
     including
    1.61
     this
    1.54
     out
    1.52
     these
    1.52
     will
    1.42
     all
    1.41
    Activations Density 0.107%

    No Known Activations