© 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. 10-GEMMASCOPE-RES-131K
    7. 86004
    Prev
    Next
    INDEX
    Explanations

    meals

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

    This neuron detects mentions of meals (and related terms like lunches).

    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
    彞
    -2.53
    ቍ
    -2.44
    鲣
    -2.41
    ᜀ
    -2.38
    AutoresizingMask
    -2.33
    他就
    -2.31
    plash
    -2.25
    昞
    -2.23
    (^_^;)
    -2.22
     髪型
    -2.22
    POSITIVE LOGITS
    al
    2.95
     The
    2.56
    ll
    2.52
    mu
    2.52
     But
    2.42
    崀
    2.34
    ra
    2.30
    的
    2.28
                
    2.27
    ized
    2.20
    Activations Density 0.004%

    No Known Activations