© 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. 22-GEMMASCOPE-RES-131K
    7. 14444
    Prev
    Next
    INDEX
    Explanations

    obligation, necessity, or requirement

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

    The neuron selectively lights up on relatively uncommon, content-bearing words (i.e. high-information tokens) rather than on frequent function words.

    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
     łatwo
    -1.16
     sàng
    -1.02
     позволит
    -0.97
     ceea
    -0.91
     lendemain
    -0.91
    就好
    -0.91
    чало
    -0.90
    tował
    -0.90
     nevoie
    -0.90
     carcasa
    -0.87
    POSITIVE LOGITS
     to
    2.45
    才能
    2.06
     because
    1.75
     כדי
    1.62
    才行
    1.58
    เพื่อ
    1.48
     inorder
    1.40
     чтобы
    1.26
    才可以
    1.17
     bazı
    1.16
    Activations Density 0.125%

    No Known Activations