© 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. 34-GEMMASCOPE-RES-131K
    7. 58189
    Prev
    Next
    INDEX
    Explanations

    based, May, This, People

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

    The neuron flags long, domain-specific (“technical” or “legal”) jargon words in academic or patent-style text.

    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
    ród
    -0.80
     imat
    -0.79
    quía
    -0.79
     Charter
    -0.74
     Sati
    -0.73
     فبراير
    -0.73
     targeted
    -0.71
    țiile
    -0.71
    วัส
    -0.71
    lyte
    -0.70
    POSITIVE LOGITS
     protocolos
    1.06
     División
    0.87
     Bisnis
    0.79
     interactive
    0.77
    protocol
    0.77
    ocas
    0.75
     acusado
    0.75
    Commitment
    0.75
     Protocols
    0.75
    ไว้
    0.75
    Activations Density 0.014%

    No Known Activations