© 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. 13263
    Prev
    Next
    INDEX
    Explanations

    system parameters and information

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

    The neuron selectively fires on long, multi-syllable content nouns (especially formal or technical terms).

    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
     within
    -1.06
    更大
    -1.05
    ність
    -1.05
    で見る
    -1.02
     takže
    -0.99
    為に
    -0.98
     faktiskt
    -0.97
    ’
    -0.96
     бать
    -0.95
     menyes
    -0.93
    POSITIVE LOGITS
    8
    1.12
    7
    1.11
     necessari
    1.10
    6
    1.08
    LOGGER
    1.06
    。"
    1.05
    5
    1.03
    !!
    1.02
    ~~
    1.02
    +
    1.01
    Activations Density 0.105%

    No Known Activations