© 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. 84291
    Prev
    Next
    INDEX
    Explanations

    portfolio

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

    The main thing this neuron does is detect occurrences of the word “portfolio.”

    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
    </i>
    -3.17
    1
    -2.78
    ⡪
    -2.20
    or
    -2.16
    </b>
    -2.05
    el
    -2.02
     —
    -1.98
    >())
    -1.97
    蛐
    -1.95
    ER
    -1.94
    POSITIVE LOGITS
     of
    2.98
    媖
    2.36
    ية
    2.30
    </h4>
    2.23
    _
    2.19
    ⋃
    2.19
    𖣔
    2.16
     jurídico
    2.13
     poética
    2.13
    ᠁
    2.03
    Activations Density 0.003%

    No Known Activations