© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49353
    Prev
    Next
    INDEX
    Explanations

    uplands and geographical features

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

    This neuron lights up on numeric information, especially quantities and measurements (e.g. distances, heights, counts, years, and units).

    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
    MethodImpl
    -0.83
     freeway
    -0.82
     виправивши
    -0.81
     Dube
    -0.81
     Kildare
    -0.80
    nipeg
    -0.79
    imax
    -0.79
     Fil
    -0.79
    tilde
    -0.79
     gew
    -0.78
    POSITIVE LOGITS
     heather
    1.24
     fell
    1.09
     sheep
    1.05
    Heather
    0.96
    Zunanje
    0.96
     peat
    0.94
     walkers
    0.93
     lambs
    0.90
     summit
    0.90
     upland
    0.89
    Activations Density 0.048%

    No Known Activations