© 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. 54170
    Prev
    Next
    INDEX
    Explanations

    breaches Section, unemployment rate, health workers

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

    programming code elements like header files, class definitions, and code syntax.

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

    This neuron activates on numeric tokens (i.e. sequences of digits).

    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
     Stille
    -0.82
    餾
    -0.77
     廠
    -0.77
    TOUCH
    -0.76
     БО
    -0.74
    Bard
    -0.73
    Pojo
    -0.72
     menetapkan
    -0.72
    subaru
    -0.72
     визна
    -0.72
    POSITIVE LOGITS
     Nigeria
    0.91
    aná
    0.83
     Nitrogen
    0.82
    Header
    0.77
    суль
    0.75
     Odds
    0.75
    tims
    0.73
     nitrogen
    0.73
    tial
    0.71
    ('--
    0.71
    Activations Density 0.001%

    No Known Activations