© 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. 31312
    Prev
    Next
    INDEX
    Explanations

    transaction protobufs

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

    The neuron fires on code‐style identifiers and type/class names (tokens in CamelCase or uppercased form such as “Tx,” “Request,” “Dependency,” “ClassificationResult,” etc.).

    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
     those
    -0.91
     such
    -0.91
    iconque
    -0.88
     fourth
    -0.88
     on
    -0.88
     until
    -0.88
     about
    -0.84
     actively
    -0.84
            
    -0.84
     second
    -0.83
    POSITIVE LOGITS
    OrBuilder
    1.20
    izó
    1.02
    still
    1.02
    Proto
    0.94
     enthou
    0.93
     Proto
    0.92
     JAXBElement
    0.92
     inond
    0.91
    皝
    0.91
    erobic
    0.90
    Activations Density 0.006%

    No Known Activations