© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15804
    Prev
    Next
    INDEX
    Explanations

    focusing on current or specified conditions

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

    The neuron fires on substantive content words (not common function words)—particularly descriptive verbs and adjectives.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    These
    -1.62
    Still
    -1.45
    If
    -1.37
     memang
    -1.35
     einem
    -1.34
     masih
    -1.34
    ámicas
    -1.32
     avait
    -1.30
     dün
    -1.30
     einer
    -1.28
    POSITIVE LOGITS
    нову
    1.40
    </
    1.24
    \
    1.23
     daarna
    1.20
    ://
    1.20
    thodoxy
    1.20
    -
    1.20
    forgettable
    1.20
     ongeveer
    1.17
     саны
    1.16
    Activations Density 0.094%

    No Known Activations