© 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. 12751
    Prev
    Next
    INDEX
    Explanations

    defined macro or keyword

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

    The neuron specifically detects occurrences of the double-pipe “||” logical-OR operator.

    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
    푣
    -2.34
    觏
    -2.20
    馐
    -2.16
     parachoque
    -2.13
    鋮
    -2.11
    Ꮘ
    -2.08
     wisata
    -2.05
     丁目
    -2.05
     排骨
    -2.03
     miniaturka
    -2.02
    POSITIVE LOGITS
    O
    2.72
    </sub>
    2.52
    ta
    2.47
    h
    2.36
    k
    2.31
    ti
    2.31
    V
    2.28
    “
    2.25
    e
    2.17
    l
    2.14
    Activations Density 0.003%

    No Known Activations