© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59351
    Prev
    Next
    INDEX
    Explanations

    case numbers and court documents

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

    The neuron is triggered by multi‐digit numeric tokens (e.g. years, percentages, identifiers, or other long numbers).

    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
    عين
    -0.79
    peicher
    -0.78
    setEmail
    -0.77
    tamanya
    -0.76
     Strip
    -0.76
    Pil
    -0.75
    setFirstName
    -0.74
    Et
    -0.73
    ätte
    -0.73
    笏
    -0.72
    POSITIVE LOGITS
     APPRO
    0.85
    changes
    0.84
     cantit
    0.82
     marvelous
    0.82
     Hinsicht
    0.81
     avem
    0.80
    enjoy
    0.79
     StringTokenizer
    0.79
    tiker
    0.78
     sayuran
    0.78
    Activations Density 0.001%

    No Known Activations