© 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. 22-GEMMASCOPE-RES-131K
    4. 75169
    Prev
    Next
    INDEX
    Explanations

    after months

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

    This neuron activates on HTML-style hexadecimal color codes (strings beginning with “#” followed by hex digits).

    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
    ДИ
    -1.40
     <",
    -1.34
     romantis
    -1.34
     hunde
    -1.33
     fotball
    -1.32
     guir
    -1.31
     Chinois
    -1.31
    𓋼
    -1.30
     Formule
    -1.30
     nacht
    -1.30
    POSITIVE LOGITS
     gegenwär
    1.30
    常用的
    1.18
     and
    1.16
     figliu
    1.14
     Auffassung
    1.10
     zweck
    1.09
     This
    1.07
    明確
    1.06
     胶
    1.06
    ährlich
    1.06
    Activations Density 0.000%

    No Known Activations