© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89812
    Prev
    Next
    INDEX
    Explanations

    Administration of

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

    This neuron activates for source code comments and copyright notices, particularly in programming files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens (digits, version numbers, and numeric literals).

    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
    move
    -0.82
    𝘷
    -0.77
     UI
    -0.77
    bumptech
    -0.73
     jsi
    -0.72
     Ziel
    -0.71
    宮城
    -0.71
    ້
    -0.70
     move
    -0.70
     encontramos
    -0.70
    POSITIVE LOGITS
     pleaf
    0.84
     aço
    0.82
    dası
    0.81
    holt
    0.79
     poffe
    0.76
    碼
    0.74
    shark
    0.74
     Receptors
    0.72
    Kite
    0.72
     essas
    0.71
    Activations Density 0.004%

    No Known Activations