© 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. 14267
    Prev
    Next
    INDEX
    Explanations

    has a description

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

    The neuron detects occurrences of the word “description” (e.g. field names or labels).

    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
    </b>
    -1.68
    )
    -1.61
    旆
    -1.55
     soooo
    -1.52
    蓠
    -1.48
     captivating
    -1.42
    geordnet
    -1.42
     stunning
    -1.42
     comical
    -1.41
     sooo
    -1.40
    POSITIVE LOGITS
     has
    1.69
    𐐪
    1.58
     laajenta
    1.57
    9
    1.57
    0
    1.57
     \
    1.50
     kommentar
    1.47
     annons
    1.44
     شیپور
    1.41
     SPAIN
    1.39
    Activations Density 0.032%

    No Known Activations