© 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. 10-GEMMASCOPE-RES-131K
    7. 9782
    Prev
    Next
    INDEX
    Explanations

    Jalapeno, Jalamadul, JAL

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

    The neuron is activated by names of plant‐based food ingredients (e.g. peppers, tomatillos, aloe vera).

    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
    </h3>
    -2.03
    are
    -1.97
     verbess
    -1.94
    爸
    -1.85
    <strong>
    -1.82
    甚至
    -1.81
    鲠
    -1.80
     desastre
    -1.80
    as
    -1.78
     controver
    -1.78
    POSITIVE LOGITS
    Surprisingly
    1.89
    \\
    1.63
    𝟐
    1.61
    يقة
    1.59
    Other
    1.53
     жив
    1.51
    🐚
    1.51
     menghasilkan
    1.51
    غيرة
    1.48
     twor
    1.43
    Activations Density 0.003%

    No Known Activations