© 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. 22-GEMMASCOPE-RES-131K
    7. 13751
    Prev
    Next
    INDEX
    Explanations

    open landscapes: plains, meadows, fields

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

    The main thing this neuron does is detect references to landscape or terrain features (e.g. plains, forests, savannas, fields).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     plazos
    -1.06
     requerimientos
    -1.02
     each
    -0.98
     británica
    -0.97
    umpang
    -0.97
    }
    -0.97
     bawat
    -0.97
     mortos
    -0.94
    REQUIRED
    -0.94
     a
    -0.93
    POSITIVE LOGITS
     paraît
    1.27
     where
    1.18
    euvres
    1.17
    новение
    1.17
    idemia
    1.11
    baseball
    1.10
    𝓼
    1.10
     of
    1.09
    尛
    1.09
    stret
    1.05
    Activations Density 0.037%

    No Known Activations