© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129606
    Prev
    Next
    INDEX
    Explanations

    The neuron flags technical operation–oriented keywords—i.e. words naming key actions or capabilities (e.g. visualization, scheduling, capture).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    actions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     it
    -1.39
     another
    -1.30
     two
    -1.25
    ったのは
    -1.24
    还有一
    -1.14
     präsentieren
    -1.13
     encantó
    -1.09
    اعة
    -1.08
     ProtoMessage
    -1.02
     گیا
    -1.02
    POSITIVE LOGITS
     you
    1.63
     such
    1.54
     zarówno
    1.49
     ilyen
    1.41
     azonban
    1.30
     entweder
    1.28
    Если
    1.27
     solche
    1.24
    Such
    1.24
     your
    1.24
    Activations Density 0.077%

    No Known Activations