© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 586
    Prev
    Next
    INDEX
    Explanations

    zero gravity and weightlessness

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

    This neuron identifies numeric tokens and quantitative expressions (numbers, measurements, and hyphenated numeric ranges).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    nerable
    -0.82
    ardom
    -0.80
    ⋮
    -0.77
    \{\\
    -0.77
    יט
    -0.75
    ]->
    -0.73
     نفر
    -0.73
     intptr
    -0.72
    })();
    -0.71
    ogados
    -0.71
    POSITIVE LOGITS
     gravity
    1.55
    gravity
    1.45
     Gravity
    1.38
     NASA
    1.34
    Gravity
    1.34
     zero
    1.26
     weight
    1.23
     astronauts
    1.21
    weight
    1.20
     floating
    1.18
    Activations Density 0.040%

    No Known Activations