© 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. 16236
    Prev
    Next
    INDEX
    Explanations

    initiating a clause, sentence, or list

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

    The neuron responds to sentence-initial discourse or temporal connectors (e.g. “In,” “During,” “While,” “This”) that introduce clauses or sections.

    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
     Deixe
    -1.08
    推荐阅读
    -1.07
     Também
    -1.06
     estúdio
    -1.03
     angenehm
    -0.99
    工程师
    -0.98
     verres
    -0.97
     Qualquer
    -0.96
    says
    -0.96
    ****
    -0.96
    POSITIVE LOGITS
     and
    1.22
     then
    1.06
     to
    0.92
     at
    0.91
     &
    0.85
    :
    0.84
     -
    0.84
     /
    0.84
     та
    0.82
    järvi
    0.81
    Activations Density 0.058%

    No Known Activations