© 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. 99432
    Prev
    Next
    INDEX
    Explanations

    quantities in tonnes

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

    The neuron detects numeric expressions of mass or weight (e.g., tonnage values).

    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
    
    -2.64
    躂
    -2.61
    ്ട
    -2.58
    葙
    -2.44
     ruinas
    -2.42
     parachoque
    -2.41
     này
    -2.39
     questo
    -2.39
    ?”
    -2.39
    𞤤
    -2.38
    POSITIVE LOGITS
     tonnes
    3.30
    "
    3.00
    на
    2.47
    あります
    2.42
    買う
    2.39
    <em>
    2.36
    榦
    2.31
    –
    2.20
     OTHER
    2.14
    ing
    2.09
    Activations Density 0.001%

    No Known Activations