© 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. 66285
    Prev
    Next
    INDEX
    Explanations

    mountain and surrounding geographical features

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

    The neuron detects references to natural landforms—especially mountains, hills, caves, etc.—in the text.

    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
    鹟
    -1.93
    …！
    -1.92
     vagab
    -1.83
     parachoque
    -1.83
    鹮
    -1.82
    
    -1.78
     壁纸
    -1.74
    酲
    -1.74
    旬
    -1.74
     BEER
    -1.73
    POSITIVE LOGITS
    -
    2.25
     ‘‘
    1.97
     stip
    1.93
     charismatic
    1.91
    )
    1.86
     ‘
    1.84
    (
    1.84
    ,,
    1.81
     [
    1.80
     знамени
    1.80
    Activations Density 0.004%

    No Known Activations