© 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. 34-GEMMASCOPE-RES-131K
    7. 56827
    Prev
    Next
    INDEX
    Explanations

    copyright year

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

    The neuron reliably lights up on numeric tokens appearing inside parentheses (e.g. version numbers or other parenthesized digits).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Equity
    -0.66
     мар
    -0.66
     Māori
    -0.65
    Hi
    -0.65
     txt
    -0.64
     Schutz
    -0.64
     diplomatic
    -0.63
     Text
    -0.63
    bbles
    -0.63
    選
    -0.62
    POSITIVE LOGITS
     OnClickListener
    0.69
    characters
    0.68
    CER
    0.68
    tour
    0.68
     recue
    0.68
     الشخصية
    0.67
    அ
    0.65
     softener
    0.65
     quartered
    0.65
    CBN
    0.65
    Activations Density 0.092%

    No Known Activations