© 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. 10458
    Prev
    Next
    INDEX
    Explanations

    Miz, spectrophotometry, predisposing, OEM

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

    scientific and technical terms related to spectrophotometry and measurement instruments.

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

    The neuron fires on the substring “Miz,” picking out that sequence wherever it appears (e.g. in names or brand tokens).

    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
    "
    -5.25
    u
    -3.70
    In
    -3.55
    as
    -3.42
    3
    -3.25
    t
    -3.08
    on
    -3.06
    en
    -3.02
    2
    -3.00
    m
    -2.78
    POSITIVE LOGITS
    硨
    3.08
    geſ
    3.00
    襠
    2.88
    ╽
    2.81
    ࿙
    2.77
    釙
    2.75
    涠
    2.69
    芣
    2.67
     celebrado
    2.61
    砗
    2.59
    Activations Density 0.007%

    No Known Activations