© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7296
    Prev
    Next
    INDEX
    Explanations

    languages, addresses, and data labels

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

    The neuron is sensitive to numeric tokens, especially decimal or integer values (i.e. numbers).

    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
     Répondre
    -1.72
    <bos>
    -1.57
     Obtén
    -1.55
    2
    -1.50
     Améli
    -1.46
     Envío
    -1.42
     Créer
    -1.41
     Choisissez
    -1.40
     Artículo
    -1.38
     Réponses
    -1.38
    POSITIVE LOGITS
    ]}$
    1.60
    PARATION
    1.52
    xFC
    1.44
    )}$.
    1.42
     exaggerated
    1.41
     вси
    1.40
    )))),
    1.40
    )),
    
    1.38
     to
    1.35
    *}$
    1.34
    Activations Density 0.012%

    No Known Activations