© 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. 34-GEMMASCOPE-RES-131K
    4. 116809
    Prev
    Next
    INDEX
    Explanations

    MAPK pathway and maples

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

    The neuron activates for the term "MAP" (often associated with "kinase" in scientific contexts) and variations of "maple" in different contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on any token containing the letters “MAP” (in any case), i.e. occurrences of “MAP” or “map” within 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_34/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
    الإنجليزية
    -0.70
     Accountability
    -0.70
     perspectiva
    -0.70
    乃是
    -0.69
     Anthony
    -0.68
     ущер
    -0.68
     samo
    -0.68
     הוצ
    -0.67
    回数
    -0.66
    twice
    -0.66
    POSITIVE LOGITS
    illai
    0.84
    zzleHttp
    0.81
    izability
    0.78
    hirkan
    0.77
     Arbor
    0.74
    alsa
    0.74
     они
    0.73
    eamento
    0.72
     germination
    0.71
    Plano
    0.71
    Activations Density 0.017%

    No Known Activations