© 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. 14569
    Prev
    Next
    INDEX
    Explanations

    code identifiers and prefixes

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

    The neuron fires on code identifier tokens that are all-uppercase acronyms (e.g. namespace or API prefixes).

    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
     Dijo
    -1.25
     bemerk
    -1.10
    --]
    -1.10
     geladen
    -1.09
     allerlei
    -1.06
     సౌ
    -1.06
     ausein
    -1.05
    Permalink
    -1.04
    tappe
    -1.03
     ähnlich
    -1.02
    POSITIVE LOGITS
     (
    1.49
     –
    1.13
     out
    1.11
     trenger
    1.10
     meget
    1.02
     tilbake
    0.97
     москве
    0.95
    地に
    0.95
    」，
    0.94
     lê
    0.94
    Activations Density 0.010%

    No Known Activations