© 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. 22-GEMMASCOPE-RES-131K
    7. 16251
    Prev
    Next
    INDEX
    Explanations

    the, a + specific noun

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

    The neuron activates on words naming or describing physical locations or structures (e.g. villa, city, home, bar).

    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
    ofing
    -1.36
    entire
    -1.16
     playera
    -1.09
     cruda
    -1.09
     felpa
    -1.08
     SCIENCES
    -1.05
     both
    -1.04
     lavable
    -1.03
    \&
    -1.03
     entière
    -1.02
    POSITIVE LOGITS
     to
    2.00
     where
    1.65
     başka
    1.23
     by
    1.20
     places
    1.16
    Médaille
    1.15
     Obtén
    1.14
    ᐈ
    1.12
     for
    1.09
     Allí
    1.09
    Activations Density 0.051%

    No Known Activations