© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72099
    Prev
    Next
    INDEX
    Explanations

    first-person statements

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

    The neuron strongly activates on tokens that start a sentence (i.e. the first word of a sentence).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     '
    -1.90
     dodgy
    -1.84
     #
    -1.83
     burgeoning
    -1.80
     sketchy
    -1.71
     jovial
    -1.69
     —
    -1.66
     fanciful
    -1.63
     new
    -1.62
    </h3>
    -1.59
    POSITIVE LOGITS
    this
    2.13
    鉭
    2.09
    ਃ
    1.99
    镚
    1.98
    during
    1.96
    糴
    1.96
     penso
    1.95
     pohon
    1.88
    ༔
    1.86
    醅
    1.85
    Activations Density 0.026%

    No Known Activations