© 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. 49722
    Prev
    Next
    INDEX
    Explanations

    code structure and properties

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

    The neuron is tuned to pick out code‐style identifiers or technical field names (e.g. headers, align, CellStyle, logging, Report, shadow, Date) in documents.

    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
    aimerais
    -0.85
    ans
    -0.80
    ens
    -0.79
    iri
    -0.77
    vi
    -0.77
    ri
    -0.77
    enna
    -0.76
     murano
    -0.74
     meant
    -0.74
     intend
    -0.74
    POSITIVE LOGITS
     аккура
    1.00
     Voter
    0.96
    uglify
    0.88
    decap
    0.87
    અ
    0.85
     pemberian
    0.84
    Xuất
    0.84
    leicht
    0.83
    הס
    0.82
    französ
    0.82
    Activations Density 0.001%

    No Known Activations