© 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. 34-GEMMASCOPE-RES-131K
    7. 55877
    Prev
    Next
    INDEX
    Explanations

    woodlands, forests, plant types, units, mapping

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

    ecological descriptions and habitat classifications in scientific text.

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

    The neuron detects mentions of ecological plant or vegetation community types (e.g. chaparral, woodlands, montane plant community).

    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
    ɲ
    -0.84
     GTS
    -0.78
    MCC
    -0.77
    ائح
    -0.76
     Courant
    -0.75
    จะมี
    -0.74
    jenih
    -0.74
     nurt
    -0.74
    UH
    -0.73
    حديد
    -0.73
    POSITIVE LOGITS
     units
    1.16
     unit
    1.14
     mapping
    1.08
     subunits
    0.91
     Unit
    0.90
     unidad
    0.88
     UNITS
    0.87
     COMPLEX
    0.86
     Mapping
    0.84
     map
    0.84
    Activations Density 0.011%

    No Known Activations