© 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. 129940
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the word “Stimulus” (specifically on its “ulus” subtoken), so it is detecting occurrences of that term.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    declarative or introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     from
    -1.55
    t
    -1.29
     If
    -1.23
    f
    -1.19
     keine
    -1.16
     their
    -1.15
     أجل
    -1.12
     From
    -1.11
    初め
    -1.08
     tirelessly
    -1.04
    POSITIVE LOGITS
    鬓
    1.34
    謌
    1.31
    
    1.26
    <bos>
    1.23
    焌
    1.21
    偲
    1.20
    
    1.20
    debate
    1.20
    􀂃
    1.19
    がたくさん
    1.18
    Activations Density 0.000%

    No Known Activations