© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 918
    Prev
    Next
    INDEX
    Explanations

    genetic drift

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

    words and concepts related to movement, drift, or change over time in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on highly technical or domain‐specific scientific terms and jargon commonly found in research abstracts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     cacher
    -0.85
    Ethio
    -0.84
     Mare
    -0.81
    Mare
    -0.81
     Rainy
    -0.79
    dedu
    -0.79
    Violence
    -0.78
     BIR
    -0.77
     Feier
    -0.76
     Violence
    -0.72
    POSITIVE LOGITS
     drift
    5.47
    drift
    4.53
     Drift
    4.53
    Drift
    4.19
     drifting
    4.13
     drifts
    3.97
     drifted
    3.94
    漂
    2.56
    rift
    2.09
     adrift
    1.92
    Activations Density 0.044%

    No Known Activations