© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71508
    Prev
    Next
    INDEX
    Explanations

    defines or specifies with "denote"

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

    The neuron activates on occurrences of the word “denote” (and its inflected forms like “denoted,” “denotes,” 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
    i
    -2.92
     awaken
    -2.36
     ingrained
    -2.34
    ?”
    -2.28
     incite
    -2.27
    ޚ
    -2.23
    その
    -2.22
    }
    -2.19
     économie
    -2.19
    towych
    -2.19
    POSITIVE LOGITS
    </sup>
    3.00
     descri
    2.75
    </h2>
    2.63
     need
    2.45
     SEVER
    2.41
    guigu
    2.38
    但在
    2.36
     halbe
    2.31
    而在
    2.30
     pertenec
    2.30
    Activations Density 0.003%

    No Known Activations