© 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. 30264
    Prev
    Next
    INDEX
    Explanations

    method signatures and code blocks

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

    The neuron activates on numeric tokens (i.e. sequences of digits).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ffins
    -0.85
     when
    -0.82
     високо
    -0.79
     пройти
    -0.76
    ૧
    -0.75
     in
    -0.73
     detuvo
    -0.73
    érieures
    -0.72
    alte
    -0.72
    toByteArray
    -0.71
    POSITIVE LOGITS
     obrazu
    0.94
    푉
    0.90
     هنا
    0.88
     ekolog
    0.86
    bluza
    0.82
    絝
    0.81
    ~(
    0.81
    MessageBox
    0.80
    足够的
    0.79
    problemas
    0.79
    Activations Density 0.003%

    No Known Activations