© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69196
    Prev
    Next
    INDEX
    Explanations

    sm following titles or names

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

    The neuron primarily activates on numeric tokens (e.g. measurements, IDs, counts, and other 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_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
    ritsar
    -1.16
    »),
    -1.11
    fähigkeit
    -1.11
    </h4>
    -1.09
    唻
    -1.09
     Савезне
    -1.04
    </h2>
    -1.04
    '])
    
    -1.03
    ]$.
    -1.02
    komt
    -1.01
    POSITIVE LOGITS
    -
    1.37
    '
    1.20
    (
    1.03
    _
    1.00
     pervasive
    0.99
     W
    0.93
    /
    0.93
     reciben
    0.93
     mingled
    0.91
     ,
    0.90
    Activations Density 0.006%

    No Known Activations