© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15542
    Prev
    Next
    INDEX
    Explanations

    enduring, timeless, permanent

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

    The main thing this neuron does is detect words and phrases evoking lastingness or permanence.

    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
     resalt
    -1.64
    犼
    -1.60
    OUTUBE
    -1.58
    はなく
    -1.40
    scul
    -1.39
     hals
    -1.31
     wana
    -1.30
    凩
    -1.28
    瑚
    -1.28
    MemoryWarning
    -1.28
    POSITIVE LOGITS
    '
    1.57
     we
    1.46
    ’
    1.42
    They
    1.41
    ”
    1.38
    ):
    1.37
    ）
    1.33
    ”:
    1.28
    T
    1.28
    ↵
    1.27
    Activations Density 0.074%

    No Known Activations