© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84801
    Prev
    Next
    INDEX
    Explanations

    cryptography and programming

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

    The neuron is tuned to pick up named technical entities—platforms, services, libraries, surveys, and other branded or acronym‐style proper names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.82
     anderen
    -1.62
    {
    -1.49
     “
    -1.47
     puramente
    -1.45
    相同的
    -1.43
     was
    -1.41
    </u>
    -1.41
     otros
    -1.38
    盥
    -1.36
    POSITIVE LOGITS
    romas
    1.63
     logistique
    1.62
    檸
    1.61
    危險
    1.53
    殞
    1.52
    驟
    1.41
    îné
    1.38
     récolte
    1.38
    盜
    1.38
     поддержку
    1.35
    Activations Density 0.033%

    No Known Activations