© 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. 86415
    Prev
    Next
    INDEX
    Explanations

    consecutive years and days

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

    This neuron detects mentions of how many times something has happened in a row (e.g. “fifth straight year,” “second consecutive month,” “third day”).

    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
    ڧ
    -1.34
    ые
    -1.32
    atoria
    -1.30
     if
    -1.27
    ggish
    -1.25
     from
    -1.23
    ılmış
    -1.22
     Ancak
    -1.21
     allow
    -1.17
    边界
    -1.17
    POSITIVE LOGITS
     our
    1.63
     nonostante
    1.49
    ---
    1.47
     alcuni
    1.42
     this
    1.42
     educativas
    1.41
     mostrando
    1.41
     some
    1.38
     Largest
    1.34
    sistence
    1.30
    Activations Density 0.038%

    No Known Activations