© 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. 71247
    Prev
    Next
    INDEX
    Explanations

    arranges and affects

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

    The neuron fires strongest on longer, specialized or less common multi‐syllable words.

    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
     instead
    -1.36
     straips
    -1.34
     permesso
    -1.21
     invito
    -1.21
     permette
    -1.21
     Infór
    -1.20
     previously
    -1.17
     confronti
    -1.16
     needed
    -1.13
     precedente
    -1.13
    POSITIVE LOGITS
     erő
    1.06
    🎟
    1.04
     both
    1.00
    ⏬
    0.98
     beiden
    0.98
     méret
    0.97
    Both
    0.96
     vagyok
    0.94
    帐户
    0.93
    ;
    0.93
    Activations Density 0.029%

    No Known Activations