© 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. 73678
    Prev
    Next
    INDEX
    Explanations

    Specific words in lists

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

    The neuron fires on standalone header or label tokens (e.g. table/section column names and other single‐word headings) in structured text.

    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
     ſp
    -1.41
     梦
    -1.39
     hina
    -1.38
     terima
    -1.37
     berkualitas
    -1.36
     menyen
    -1.34
     tampaknya
    -1.34
     vitaminas
    -1.34
    ью
    -1.33
     thoſe
    -1.33
    POSITIVE LOGITS
    /
    1.50
    (
    1.45
     (
    1.41
     katika
    1.30
     
    1.28
    —
    1.23
    msub
    1.19
    __":
    1.15
     子ども
    1.12
     previous
    1.10
    Activations Density 0.001%

    No Known Activations