© 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. 34-GEMMASCOPE-RES-131K
    7. 90041
    Prev
    Next
    INDEX
    Explanations

    "Spring response" or "Vascular function"

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

    comment blocks in programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is keyed to Javadoc‐style comment delimiters (the /** … * lines in Java doc comment blocks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     capacité
    -0.94
     Schluss
    -0.81
    iją
    -0.79
    ﻹ
    -0.78
    johtaja
    -0.78
     kuning
    -0.76
    ARROLL
    -0.76
    łego
    -0.76
     oleh
    -0.75
    ać
    -0.74
    POSITIVE LOGITS
    痛み
    0.84
     diferença
    0.82
    大きさ
    0.81
    ناک
    0.80
     nien
    0.80
    𝕣
    0.79
    的眼
    0.76
     tutt
    0.75
     разные
    0.74
    hus
    0.74
    Activations Density 0.006%

    No Known Activations