© 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. 22-GEMMASCOPE-RES-131K
    7. 38210
    Prev
    Next
    INDEX
    Explanations

    a way to do something

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

    This neuron detects discourse markers that introduce alternative solutions or methods—words like “One,” “Another,” “approach,” “solution,” etc.

    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
    也沒
    -1.21
    uating
    -1.10
    aked
    -1.09
    ează
    -1.07
    ConstraintMaker
    -1.06
    웬
    -1.02
     понадоби
    -1.02
    ;<
    -1.02
    軽い
    -0.99
    wasn
    -0.98
    POSITIVE LOGITS
     if
    2.36
     may
    1.91
     might
    1.76
     you
    1.76
     can
    1.70
     by
    1.69
     could
    1.66
     option
    1.65
     but
    1.65
     to
    1.54
    Activations Density 0.106%

    No Known Activations