© 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. 34-GEMMASCOPE-RES-131K
    7. 78071
    Prev
    Next
    INDEX
    Explanations

    state of charge

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

    The neuron identifies numeric tokens (digits, numeric constants, and parameter values) in technical or mathematical contexts.

    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
     tulis
    -0.83
    toggler
    -0.82
     konsep
    -0.82
    Navigator
    -0.82
    ︠
    -0.78
    Checker
    -0.78
     sukses
    -0.77
    ức
    -0.75
    Picker
    -0.75
    arquia
    -0.74
    POSITIVE LOGITS
     dynamics
    0.98
     inertia
    0.96
     BLA
    0.85
     mass
    0.82
     位置
    0.81
    ísica
    0.81
     Radcliffe
    0.81
    ば
    0.80
    頂き
    0.80
     inertial
    0.79
    Activations Density 0.007%

    No Known Activations