© 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. 10-GEMMASCOPE-RES-131K
    7. 111907
    Prev
    Next
    INDEX
    Explanations

    sequence of

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

    The neuron strongly fires on the token “of,” especially when it appears in identifiers or dotted names (e.g. “value_of,” “SizeOfBuffer,” “divisorOf,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ):
    -1.76
    brazilian
    -1.66
    leopard
    -1.63
     subido
    -1.63
     algemene
    -1.63
     espectro
    -1.60
     pernyataan
    -1.59
     efisien
    -1.57
    %;
    -1.53
     résister
    -1.53
    POSITIVE LOGITS
    s
    2.39
    2
    2.20
    0
    1.94
    。
    1.84
    “
    1.83
    —
    1.81
    ’
    1.76
    href
    1.63
    니다
    1.57
     them
    1.54
    Activations Density 0.039%

    No Known Activations