© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72506
    Prev
    Next
    INDEX
    Explanations

    state or transition point

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

    The neuron responds to words that signal progress toward or attainment of a milestone (e.g., off, narrowed, gap, go, deal, point, pulled, marginal, even).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.98
     llavero
    -1.76
     adopción
    -1.54
     soldadura
    -1.49
     silicona
    -1.47
     bezw
    -1.47
     financiación
    -1.46
     aparatos
    -1.45
     понравился
    -1.42
     entornos
    -1.41
    POSITIVE LOGITS
     to
    3.61
     in
    2.98
     of
    2.69
     on
    2.56
     for
    2.34
     when
    2.33
     regarding
    1.72
     with
    1.58
     if
    1.52
     by
    1.51
    Activations Density 0.084%

    No Known Activations