© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67317
    Prev
    Next
    INDEX
    Explanations

    citations and names

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

    The neuron is keyed to bibliographic reference tokens, especially author initials and similar single‐letter citation markers in reference lists.

    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
     and
    -3.59
     และ
    -1.38
     và
    -1.36
    และ
    -1.36
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.34
    (!_
    -1.32
     и
    -1.30
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.27
    ...!
    -1.25
    ↵↵↵↵↵↵↵↵↵↵
    -1.23
    POSITIVE LOGITS
     in
    1.85
     (
    1.59
     are
    1.44
     after
    1.27
    Kesimpulan
    1.20
    Langkah
    1.19
     skrev
    1.18
    Анна
    1.17
     for
    1.16
     bakgrund
    1.16
    Activations Density 0.006%

    No Known Activations