© 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. 36095
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

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

    The neuron consistently lights up on declarative, expository prose (e.g. article‐style or answer text) and stays off for question prompts or headings.

    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
    ваться
    -1.19
     our
    -1.19
    Sábado
    -1.16
    cuál
    -1.16
    </em>
    -1.16
     I
    -1.13
     detergente
    -1.11
     gelişti
    -1.09
     andere
    -1.08
    </strong>
    -1.06
    POSITIVE LOGITS
     deportivas
    1.40
     deportivos
    1.37
     音乐
    1.30
    Caracteristici
    1.29
     debió
    1.29
     mehrm
    1.24
    ẫn
    1.20
     obtuvo
    1.19
    ったのは
    1.18
     lãng
    1.17
    Activations Density 0.009%

    No Known Activations