© 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. 21553
    Prev
    Next
    INDEX
    Explanations

    the same

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

    The neuron fires most strongly on very high‐frequency function words (e.g. “the”, “same”).

    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
     anúncio
    -1.87
     it
    -1.85
     kawasan
    -1.76
    ()"
    -1.71
     of
    -1.70
    !!"
    -1.69
    ↵↵
    -1.67
     "
    -1.64
    ,"
    -1.63
     mulus
    -1.58
    POSITIVE LOGITS
      
    1.63
    最为
    1.59
    ſu
    1.53
    来讲
    1.52
    考验
    1.45
    来说
    1.42
    Состав
    1.41
    </h3>
    1.38
    來說
    1.37
            
    1.36
    Activations Density 0.046%

    No Known Activations