© 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. 10-GEMMASCOPE-RES-131K
    7. 60353
    Prev
    Next
    INDEX
    Explanations

    distillery, helminths, yml

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

    references to distilleries, distilling processes, and related terminology.

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

    The neuron consistently fires on words containing the stem “distill” (e.g. Distillery, distilling, distillative).

    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
    </strong>
    -2.81
     offizielle
    -2.67
    ين
    -2.63
    5
    -2.56
     leftover
    -2.47
    that
    -2.47
    -"
    -2.47
    $
    -2.45
    0
    -2.44
     manchen
    -2.39
    POSITIVE LOGITS
    er
    3.52
    an
    3.06
     剤
    3.03
    a
    2.89
    s
    2.70
    erintah
    2.56
    zelfde
    2.44
     fundamentos
    2.42
     美容
    2.39
    برها
    2.36
    Activations Density 0.012%

    No Known Activations