© 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. 10-GEMMASCOPE-RES-131K
    7. 119007
    Prev
    Next
    INDEX
    Explanations

    articles followed by common words

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

    The neuron lights up on very high‐frequency “function” words (common stop words) such as any, this, you, it, of, in, a, way, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -2.00
    時間に
    -1.59
    -
    -1.59
    Generally
    -1.48
    These
    -1.48
     prevents
    -1.47
     вона
    -1.44
    你和
    -1.44
    他和
    -1.44
    After
    -1.43
    POSITIVE LOGITS
    quê
    1.59
    ESSA
    1.55
    BOURNE
    1.55
     😊
    1.52
     mobilier
    1.52
    乄
    1.49
    🥲
    1.47
    DALE
    1.45
    😭
    1.45
    ͛
    1.45
    Activations Density 0.071%

    No Known Activations