© 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. 106400
    Prev
    Next
    INDEX
    Explanations

    data structures and objects

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

    The neuron fires on numeric tokens (standalone numbers and numeric literals).

    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
     Deze
    -0.79
    isPrime
    -0.79
    (_,
    -0.77
     Mueller
    -0.76
    cad
    -0.76
    anyard
    -0.76
    })$.
    -0.75
    rebro
    -0.73
     eV
    -0.73
     Blvd
    -0.72
    POSITIVE LOGITS
     Object
    1.07
     object
    0.95
    Object
    0.89
     Belakang
    0.86
     undefined
    0.84
    object
    0.81
    swatch
    0.79
     dismissed
    0.78
    Ljava
    0.76
     Underwear
    0.76
    Activations Density 0.096%

    No Known Activations