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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25759
    Prev
    Next
    INDEX
    Explanations

    configuration options

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

    The neuron is primarily looking for numeric literals (version numbers, config values, counts, and other digit‐based tokens) in code and markup.

    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
     flames
    -0.72
     vec
    -0.69
     windows
    -0.68
    ูน
    -0.68
     blend
    -0.68
    vec
    -0.68
    nger
    -0.68
    calaure
    -0.68
     fellowship
    -0.66
     kelompok
    -0.65
    POSITIVE LOGITS
     artigian
    0.77
    Acceptance
    0.75
     Fulfillment
    0.70
     Boyz
    0.70
     obiettivo
    0.70
     acceptance
    0.68
     comigo
    0.67
     konkre
    0.67
    вия
    0.66
     男孩
    0.65
    Activations Density 0.058%

    No Known Activations