© 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. 101122
    Prev
    Next
    INDEX
    Explanations

    "si" followed by verbs or sentence continuations

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

    The neuron is triggered by occurrences of the two-letter token “si.”

    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
    ↵
    -2.70
    0
    -2.42
     –
    -2.38
    筇
    -2.30
     —
    -2.30
    ly
    -2.02
    と
    -1.99
    },
    -1.98
    </h1>
    -1.96
     و
    -1.96
    POSITIVE LOGITS
    瑒
    2.64
    哢
    2.41
    棪
    2.31
     temprano
    2.11
     auténtica
    2.06
    鹮
    2.06
     reconocida
    2.05
    fatalError
    2.05
     artesanal
    2.02
     contamos
    2.02
    Activations Density 0.000%

    No Known Activations