© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12899
    Prev
    Next
    INDEX
    Explanations

    null, 0, true, "", None

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

    The neuron activates on literal constant tokens (e.g. null, None, true, numeric literals).

    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
     which
    -1.20
    They
    -1.10
     other
    -1.09
     so
    -1.05
     will
    -1.03
     no
    -1.03
     altre
    -0.99
     just
    -0.98
     etc
    -0.94
     don
    -0.93
    POSITIVE LOGITS
    vatel
    1.23
     کردی
    1.12
    НИМА
    1.11
     suyo
    1.09
     mít
    1.06
    ₗ
    1.05
     haberse
    1.03
     MEMORY
    1.02
     recibido
    1.02
    ITER
    1.01
    Activations Density 0.009%

    No Known Activations