© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112666
    Prev
    Next
    INDEX
    Explanations

    abandoned buildings and places

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

    The main thing this neuron does is detect words describing abandoned or neglected places and structures.

    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
     gratuite
    -1.54
     to
    -1.44
    ∎
    -1.42
    ra
    -1.42
     obstru
    -1.41
     QUÉ
    -1.38
    cisi
    -1.36
     francese
    -1.34
     travailler
    -1.34
    ية
    -1.34
    POSITIVE LOGITS
     in
    1.77
     abandoned
    1.73
     other
    1.71
     These
    1.57
     there
    1.57
     it
    1.56
     znajdują
    1.55
     decoradas
    1.45
    晅
    1.44
     on
    1.43
    Activations Density 0.012%

    No Known Activations