© 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. 36621
    Prev
    Next
    INDEX
    Explanations

    places and destinations

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

    This neuron detects nouns naming locations or expansive settings (e.g., jungle, border, sea, galaxy).

    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
     vrais
    -0.94
    を行い
    -0.93
    くれます
    -0.92
    kých
    -0.91
     circonst
    -0.90
    Mozilla
    -0.90
     横浜
    -0.89
     föld
    -0.89
    僳
    -0.88
     huwa
    -0.88
    POSITIVE LOGITS
     or
    1.48
     for
    1.23
     instead
    1.16
     while
    1.15
     because
    1.09
     after
    0.97
     happy
    0.97
     to
    0.96
     where
    0.92
     if
    0.91
    Activations Density 0.032%

    No Known Activations