© 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. 15425
    Prev
    Next
    INDEX
    Explanations

    first-time

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

    The neuron activates on phrases denoting “first-time” occurrences (i.e. hyphenated or explicit “first-time” references).

    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
      
    -2.39
    \
    -2.38
    <bos>
    -1.85
     учетом
    -1.78
     It
    -1.74
    戽
    -1.72
     utilizados
    -1.71
    }$
    -1.66
            
    -1.66
    maxn
    -1.65
    POSITIVE LOGITS
    ſelves
    2.28
     They
    1.96
     @"/
    1.80
    ጺ
    1.80
    
    1.77
     管
    1.76
    vám
    1.75
    your
    1.75
     火鍋
    1.72
    摃
    1.70
    Activations Density 0.010%

    No Known Activations