© 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. 129934
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the exact token “as.”

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

    names or topics followed by details

    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
    itudinal
    -1.06
     fleste
    -1.05
    ="",
    -1.04
    itys
    -1.01
    arching
    -1.00
    tuigen
    -1.00
    tismo
    -0.97
    ख़
    -0.97
    >//
    -0.96
    aning
    -0.94
    POSITIVE LOGITS
     '
    1.10
     has
    0.96
    以来
    0.93
     estará
    0.91
    t
    0.90
    B
    0.90
    But
    0.90
     is
    0.88
     Contrary
    0.87
     By
    0.85
    Activations Density 0.000%

    No Known Activations