© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 131058
    Prev
    Next
    INDEX
    Explanations

    This neuron does not activate on any of the given tokens (i.e., it remains inactive).

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

    URL placeholders and citations

    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
    焄
    -2.67
    沇
    -2.64
     utterly
    -2.58
     makeshift
    -2.48
    ſelves
    -2.48
     groundbreaking
    -2.41
     meticulously
    -2.41
     ingenious
    -2.39
     intensely
    -2.38
     exquisitely
    -2.38
    POSITIVE LOGITS
     verschillende
    2.69
    鲠
    2.69
     decidedly
    2.69
    粜
    2.67
    r
    2.64
    鵙
    2.45
    ',
    2.45
     étaient
    2.39
     atteindre
    2.39
     specif
    2.38
    Activations Density 0.005%

    No Known Activations