© 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. 38791
    Prev
    Next
    INDEX
    Explanations

    Pan-American, Dictyostelium, heat

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

    technical or programming-related content with deep nesting or hierarchical structure.

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

    The neuron lights up on domain-specific technical terms (e.g. “Handlers,” “heat”).

    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
     it
    -1.28
    -
    -1.23
     wasn
    -1.00
     posición
    -0.98
    ヨーク
    -0.97
     agresión
    -0.94
    を終
    -0.94
    рѣ
    -0.91
    慷
    -0.89
     Wikipédia
    -0.88
    POSITIVE LOGITS
    互联网档案馆
    1.04
    likation
    1.01
     kebersihan
    0.96
    M
    0.95
     cuaca
    0.95
    исленность
    0.95
    циями
    0.94
     Giappone
    0.93
    Isso
    0.93
    adesivo
    0.93
    Activations Density 0.000%

    No Known Activations