© 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. 34-GEMMASCOPE-RES-131K
    4. 59957
    Prev
    Next
    INDEX
    Explanations

    for you

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

    The neuron predominantly fires on content‐bearing words—main nouns and verbs that carry the core meaning of a sentence.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    薄
    -0.72
    ranslated
    -0.69
    chada
    -0.67
    uristic
    -0.67
     conversar
    -0.65
    △
    -0.65
     ライブ
    -0.64
    baan
    -0.64
    trina
    -0.64
     Kult
    -0.64
    POSITIVE LOGITS
     עבור
    2.16
     بالنسبة
    1.54
     hộ
    1.33
     sizin
    1.24
     åt
    1.24
     számára
    1.23
    forme
    1.21
     मेरे
    1.20
     benim
    1.20
     bagi
    1.19
    Activations Density 0.034%

    No Known Activations