© 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. 35254
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    This neuron fires on standalone “o” tokens (i.e. the single character o).

    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
    In
    -2.30
    E
    -2.19
    P
    -2.08
    A
    -2.08
    C
    -2.08
    L
    -2.06
    R
    -2.02
    W
    -2.00
    "
    -1.96
    H
    -1.96
    POSITIVE LOGITS
    และ
    2.36
     wła
    1.98
    ſſen
    1.98
     ſou
    1.90
     ſta
    1.88
    ₶
    1.84
    鹩
    1.83
    
    1.80
    ⃤
    1.79
     neceſſ
    1.78
    Activations Density 0.010%

    No Known Activations