© 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. 42981
    Prev
    Next
    INDEX
    Explanations

    introduces statements or examples

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

    The neuron strongly activates at sentence boundaries, especially on sentence-final periods and the first word of the next sentence.

    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
     vinaigre
    -1.71
     também
    -1.70
    着一个
    -1.70
     rédaction
    -1.60
    もあった
    -1.56
    もあって
    -1.55
     also
    -1.53
    Cela
    -1.52
     także
    -1.51
     навіть
    -1.50
    POSITIVE LOGITS
     your
    1.52
    =?,
    1.48
     zis
    1.45
     recent
    1.41
     nasze
    1.41
     or
    1.39
     recently
    1.38
     previous
    1.34
     piace
    1.31
     ruft
    1.31
    Activations Density 4.602%

    No Known Activations