© 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. 92436
    Prev
    Next
    INDEX
    Explanations

    finding prime factors

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

    This neuron detects tokens involved in asking for or stating prime‐factorization (e.g. “prime,” “factors,” and multi-digit number tokens).

    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
     Octobre
    -0.76
     Negara
    -0.73
     Decoder
    -0.71
     Satan
    -0.71
     CHARLES
    -0.70
     asemenea
    -0.69
    seb
    -0.69
    seek
    -0.69
     Prefix
    -0.68
     Passengers
    -0.68
    POSITIVE LOGITS
     prime
    2.25
     primes
    1.83
     Prime
    1.74
    Prime
    1.62
    prime
    1.55
     PRIME
    1.38
    primes
    1.30
    PRIME
    1.30
     primed
    1.21
    Primes
    1.15
    Activations Density 0.061%

    No Known Activations