© 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. 67167
    Prev
    Next
    INDEX
    Explanations

    Show followed by room

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

    The neuron detects double-quote characters in the 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_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
     these
    -1.23
     only
    -1.13
     allow
    -1.01
     operates
    -1.01
    ૉ
    -1.00
     protects
    -1.00
    ֢
    -0.99
     zaragoza
    -0.98
     during
    -0.98
     безпе
    -0.98
    POSITIVE LOGITS
    ̴
    1.09
     unserer
    1.07
    出色
    1.06
    essentially
    1.04
     Beiträge
    1.02
    ïn
    0.94
    sup
    0.93
     nowe
    0.93
    actually
    0.92
    gives
    0.92
    Activations Density 0.000%

    No Known Activations