© 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. 22-GEMMASCOPE-RES-131K
    4. 68812
    Prev
    Next
    INDEX
    Explanations

    technical configuration parameters

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

    The neuron strongly activates on programming‐or API‐related acronyms and technical identifiers (e.g. “URL,” “IP,” “CSV,” “OAuth,” 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_22/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
    pherds
    -1.27
     tanques
    -1.23
     MÁS
    -1.22
     fatiga
    -1.22
     bailarina
    -1.20
     könig
    -1.20
     nagyobb
    -1.20
     moletom
    -1.17
     bené
    -1.16
    geführten
    -1.14
    POSITIVE LOGITS
     for
    1.90
     or
    1.56
     that
    1.50
     whose
    1.41
     which
    1.41
     will
    1.34
     of
    1.29
     who
    1.21
     الذي
    1.20
     can
    1.20
    Activations Density 0.018%

    No Known Activations