© 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. 22-GEMMASCOPE-RES-131K
    7. 72470
    Prev
    Next
    INDEX
    Explanations

    measurements and sizes

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

    The neuron activates on numeric tokens (measurements, sizes, weights, prices, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Ẩ
    -1.11
    продам
    -1.05
     Fußballspieler
    -1.02
     ilustracji
    -0.99
     ungewöhn
    -0.98
     ομά
    -0.97
     Vergnügen
    -0.96
    吖
    -0.96
    西方
    -0.94
     lustige
    -0.93
    POSITIVE LOGITS
    our
    1.17
    ικός
    1.06
     our
    1.04
    ophones
    1.04
    ITY
    1.01
    Truth
    1.01
    ANDO
    1.00
    ſtra
    0.96
    show
    0.96
    vgili
    0.94
    Activations Density 0.002%

    No Known Activations