© 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. 130392
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on occurrences of the word “tank.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    tank

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    -2.86
    1
    -2.34
    7
    -2.31
    3
    -2.28
     drenched
    -2.28
    摃
    -2.25
     zorgt
    -2.20
     torner
    -2.16
    真的
    -2.08
    ญี่ป
    -2.08
    POSITIVE LOGITS
     citada
    2.42
     אם
    2.33
     карту
    2.30
    😸
    2.30
     mencion
    2.28
     Näch
    2.19
    
    2.19
     siapa
    2.19
    🤙
    2.17
    ЛИ
    2.16
    Activations Density 0.006%

    No Known Activations