© 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. 53991
    Prev
    Next
    INDEX
    Explanations

    'into' followed by descriptive phrases

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

    The neuron consistently activates on the word “into.”

    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
    J
    -1.47
    M
    -1.44
    ↵
    -1.42
    .
    -1.41
     klassische
    -1.39
    D
    -1.38
     üblichen
    -1.30
     vollständige
    -1.29
    but
    -1.25
     einzigartige
    -1.24
    POSITIVE LOGITS
    duced
    1.60
     the
    1.59
     Özel
    1.29
     bleue
    1.24
    zete
    1.23
     maestra
    1.21
    蟜
    1.21
     voor
    1.21
    xic
    1.19
    diese
    1.19
    Activations Density 0.075%

    No Known Activations