© 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. 6692
    Prev
    Next
    INDEX
    Explanations

    silent and drive death film lightning auction period meeting

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

    The neuron responds whenever the word “silent” appears (in any context or compound).

    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
    ⧠
    -2.81
     his
    -2.41
    am
    -2.33
     работают
    -2.31
    氿
    -2.23
    ↵
    -2.23
    菝
    -2.22
     &
    -2.20
    了下来
    -2.20
     mesmas
    -2.19
    POSITIVE LOGITS
    }
    3.83
    🫔
    3.42
    齶
    2.80
    𓋼
    2.78
    ۉ
    2.72
    With
    2.70
     That
    2.53
     achieves
    2.50
     Through
    2.47
    Without
    2.45
    Activations Density 0.002%

    No Known Activations