© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14882
    Prev
    Next
    INDEX
    Explanations

    power units

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

    The neuron fires on mentions of power‐measurement units and their values (e.g. “mega watt,” “MW,” “kW,” “MWh”).

    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
     mentre
    -1.80
     mismos
    -1.63
     mesmos
    -1.59
    ⸩
    -1.59
    ↵
    -1.55
    全是
    -1.53
    𖤍
    -1.53
     結婚
    -1.51
     quaisquer
    -1.51
     tylko
    -1.50
    POSITIVE LOGITS
    Ꮉ
    1.96
     of
    1.77
    PLICATION
    1.67
    </sup>
    1.65
    ですので
    1.63
    𝐨
    1.55
     menghadirkan
    1.51
     not
    1.45
    homonymie
    1.43
    Giới
    1.43
    Activations Density 0.004%

    No Known Activations