© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66166
    Prev
    Next
    INDEX
    Explanations

    Pod, podcasting, Podmokly, Podkamennaya, Podberezkin

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

    The neuron activates on any token containing the substring “pod” (in any casing).

    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
     This
    -2.80
    .
    -2.47
     That
    -2.42
    
    -2.25
     schlechte
    -2.17
    that
    -2.14
    
    -2.09
    脔
    -2.05
    咔
    -2.03
    聍
    -2.03
    POSITIVE LOGITS
    \
    2.72
     eléctrico
    2.52
    ↵↵
    2.30
    medriver
    2.27
    </blockquote>
    2.19
    ostí
    2.09
    鼱
    2.08
     realising
    2.06
    饜
    2.06
    々に
    2.05
    Activations Density 0.003%

    No Known Activations