© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112146
    Prev
    Next
    INDEX
    Explanations

    early and late developmental stages

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

    The neuron identifies words related to temporal stages of development or processes, particularly focusing on "early" and "late" stages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ↵
    -1.79
     a
    -1.79
    ごめん
    -1.76
      
    -1.74
    栊
    -1.66
     necesit
    -1.62
     decidi
    -1.58
     nachfol
    -1.57
    十分的
    -1.55
     lmao
    -1.52
    POSITIVE LOGITS
     These
    2.31
     Compared
    2.13
     While
    2.11
    Deskripsi
    2.11
     Every
    1.91
     plethora
    1.89
    Beskrivning
    1.89
     Even
    1.85
     After
    1.84
    メリカ
    1.84
    Activations Density 0.034%

    No Known Activations