© 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. 34-GEMMASCOPE-RES-131K
    7. 108207
    Prev
    Next
    INDEX
    Explanations

    actions or process steps

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

    The neuron flags technical procedural language—terms that describe tools, methods, processes, and steps in instructional 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
     slecht
    -0.89
    日が
    -0.87
     молодых
    -0.82
     скриншот
    -0.82
    fiable
    -0.81
     skon
    -0.77
     prawa
    -0.77
     controversy
    -0.75
     wykonania
    -0.74
     izdel
    -0.73
    POSITIVE LOGITS
     radikal
    1.04
    การ
    1.01
     implementation
    0.94
     korrekt
    0.92
    Ganz
    0.92
     ideolog
    0.91
     kafe
    0.90
     vern
    0.88
     stoff
    0.87
     kram
    0.87
    Activations Density 0.034%

    No Known Activations