© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25858
    Prev
    Next
    INDEX
    Explanations

    sequence of words and punctuation

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

    The neuron strongly activates on tokens that begin a new sentence (i.e. sentence‐initial words and the period marking the end of the previous 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_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
    possible
    -0.97
     konstant
    -0.89
    tempt
    -0.89
    kauf
    -0.86
    stopp
    -0.82
    canos
    -0.81
    pernicus
    -0.81
    Eventually
    -0.80
     if
    -0.79
    successfully
    -0.79
    POSITIVE LOGITS
     then
    2.33
     proceeded
    1.36
    Then
    1.25
     THEN
    1.16
     thereupon
    1.15
     thereafter
    1.12
     subsequently
    1.12
     subsequent
    1.09
     proceeding
    1.03
     immediately
    1.02
    Activations Density 0.045%

    No Known Activations