© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11024
    Prev
    Next
    INDEX
    Explanations

    technical and domain-specific terms

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

    The neuron fires strongly on technical terms for physical components, machinery parts, or engineering structures.

    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
    為に
    -1.49
     húmedo
    -1.48
     tatuajes
    -1.46
    つづく
    -1.45
    ビックリ
    -1.44
     tirantes
    -1.41
    に入れる
    -1.41
     hongos
    -1.40
    のではない
    -1.35
    すっ
    -1.34
    POSITIVE LOGITS
     during
    1.90
     as
    1.63
     through
    1.49
     when
    1.44
     until
    1.38
     throughout
    1.38
     each
    1.35
     by
    1.30
    ствовать
    1.28
    ？』
    1.27
    Activations Density 0.075%

    No Known Activations