© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34047
    Prev
    Next
    INDEX
    Explanations

    company configurations

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

    The neuron fires on content‐bearing tokens—especially numbers, technical terms, proper nouns, and other informational words—while largely ignoring common 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
     disregarding
    -2.67
     solidly
    -2.55
     comprehensively
    -2.45
     powerfully
    -2.44
     intrinsically
    -2.44
     rigorously
    -2.42
     mysteriously
    -2.41
     embarking
    -2.39
     indulging
    -2.39
     vividly
    -2.38
    POSITIVE LOGITS
    さんが
    1.68
     --
    1.46
    さんの
    1.38
    さんも
    1.31
    さんに
    1.20
    さんを
    1.18
    ちゃんが
    1.06
    ”？
    1.05
    좆
    1.05
     هذا
    1.04
    Activations Density 54.165%

    No Known Activations