© 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. 10-GEMMASCOPE-RES-131K
    7. 112288
    Prev
    Next
    INDEX
    Explanations

    night rentals

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

    The neuron activates on occurrences of “night” (including “nights” or “night’s”) as a time‐unit mention.

    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
    {
    -2.67
    f
    -1.70
    i
    -1.59
    x
    -1.59
    k
    -1.54
    z
    -1.54
     jaket
    -1.52
    ill
    -1.44
     when
    -1.39
     alha
    -1.39
    POSITIVE LOGITS
    zdroj
    1.64
    Iya
    1.56
     agricultores
    1.45
    ahuje
    1.45
     a
    1.45
    ⑊
    1.38
     sementes
    1.38
     stratég
    1.34
     "
    1.34
    seperti
    1.34
    Activations Density 0.012%

    No Known Activations