© 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. 113501
    Prev
    Next
    INDEX
    Explanations

    expressing purpose or value

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

    The neuron fires on words that introduce numerical evaluations or measurable quantities (e.g. “good for,” “rated at,” “capacity of,” “rate of”).

    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
     it
    -1.88
     other
    -1.74
     what
    -1.66
     verdaderas
    -1.52
     kupa
    -1.50
     seleccionadas
    -1.49
    jedno
    -1.48
     pomys
    -1.45
     how
    -1.44
     princí
    -1.41
    POSITIVE LOGITS
    一趟
    1.59
     lança
    1.58
    了一個
    1.57
    int
    1.55
    led
    1.54
    lable
    1.52
    ted
    1.49
    ren
    1.45
     lediglich
    1.45
     século
    1.42
    Activations Density 0.046%

    No Known Activations