© 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. 16125
    Prev
    Next
    INDEX
    Explanations

    events following procedures

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

    The neuron fires on temporal (and related sequential) prepositions—words like “after,” “following,” or “during” that introduce timing/sequence.

    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
    適量
    -1.07
    日が
    -1.01
     according
    -1.01
     soggior
    -0.99
    謄
    -0.98
     psicología
    -0.96
    datei
    -0.95
    Mechanics
    -0.94
    調味料
    -0.92
    add
    -0.91
    POSITIVE LOGITS
    際には
    1.27
    際に
    1.22
    つづく
    1.19
    矚
    1.19
    えっ
    1.18
    ウィキ
    1.16
    ,:);
    1.12
    ⌉
    1.12
    を目指す
    1.09
    这些人
    1.05
    Activations Density 0.097%

    No Known Activations