© 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. 68607
    Prev
    Next
    INDEX
    Explanations

    on a surface

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

    The neuron fires on the formal legal/technical adverb “thereon.”

    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
    O
    -3.19
    d
    -2.89
    鸸
    -2.56
     of
    -2.45
    靫
    -2.27
    也只是
    -2.20
    }}
    -2.20
    Ꭳ
    -2.16
    дѣ
    -2.14
    quelize
    -2.08
    POSITIVE LOGITS
    ⸫
    2.67
    .),
    2.61
    他的
    2.48
    "
    2.47
    齪
    2.42
    蔘
    2.36
     inconceivable
    2.31
     ของ
    2.30
     adalah
    2.25
    litude
    2.25
    Activations Density 0.001%

    No Known Activations